From comp.ai.neural-nets@DST.BOLTZ.CS.CMU.EDU Mon Jul 1 07:25:08 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id HAA11526 for ; Mon, 1 Jul 1996 07:25:01 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id HAA01059 for ; Mon, 1 Jul 1996 07:24:59 -0500 Message-Id: <199607011224.HAA01059@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa24793; 1 Jul 96 5:32:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa24789; 1 Jul 96 5:12:15 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05297; 1 Jul 96 5:11:32 EDT Received: from DST.BOLTZ.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa23604; 30 Jun 96 3:40:36 EDT Date: Sun, 30 Jun 96 03:40:20 EDT From: forwarded To: connectionists@cs.cmu.edu Subject: ECAI NNSK Workshop Program and Call for Participation ECAI'96 Workshop on NEURAL NETWORKS AND STRUCTURED KNOWLEDGE (NNSK) August 12, 1996 during the 12th European Conference on Artificial Intelligence August 12-16, 1996 in Budapest, Hungary Call for Participation ------------------------------------------------------------------------------- Latest information can be retrieved from the NNSK WWW-page http://www.informatik.uni-ulm.de/fakultaet/abteilungen/ni/ECAI-96/NNSK.html BACKGROUND ---------- Neural networks mostly are used for tasks dealing with information presented in vector or matrix form, without a rich internal structure reflecting relations between different entities. In some application areas, e.g. speech processing or forecasting, types of networks have been investigated for their ability to represent sequences of input data. Whereas approaches to use neural networks for the representation and processing of structured knowledge have been around for quite some time, especially in the area of connectionism, they frequently suffer from problems with expressiveness, knowledge acquisition, adaptivity and learning, or human interpretation. In the last years much progress has been made in the theoretical understanding and the construction of neural systems capable of representing and processing structured knowledge in an adequate way, while maintaining essential capabilities of neural networks such as learning, tolerance of noise, treatment of inconsistencies, and parallel operation. The goal of this workshop is twofold: On one hand, existing mechanisms are critically examined with respect to their suitability for the acquisition, representation, processing and interpretation of structured knowledge. On the other hand, new approaches, especially concerning the design of systems based on such mechanisms, are presented, with particular emphasis on their application to realistic problems. PRELIMINARY WORKSHOP PROGRAM ---------------------------- 8:30 - 8:50 INTRODUCTION (F. Kurfess) 8:50 - 10:10 SYMBOLIC INFERENCE IN CONNECTIONIST SYSTEMS 8:50 Semantic Knowledge in General Neural Units: Issues of Representation (J. de L. Pereira Castro) 9:10 Implementation of a SHRUTI Knowledge Representation and Reasoning System (R. Hayward, J. Diederich) 9:30 A Connectionist Representation of Symbolic Components, Dynamic Bindings and Basic Inference Operations (N. Seog Park, D. Robertson) 9:50 Logical Inference and Inductive Learning (A.S. d'Avila Garcez, G. Zaverucha, L.A.V. de Carvalho) 10:10 - 10:20 Discussion 10:30 - 11:00 Break 11:00 - 11:40 EXPLOITING PROBLEM-INHERENT STRUCTURED META-KNOWLEDGE 11:00 Declarative Heuristics for Neural Network Design (M. Vuilleumier, M. Hilario) 11:20 Sign Recognition as a Support to Robot Navigation (G. Adorni, G. Destri, M. Gori, M. Mordonini) 11:40 - 12:00 Discussion 12:00 - 13:45 Break 13:45 - 14:45 SUPERVISED INDUCTIVE INFERENCE ON STRUCTURED DOMAINS 13:45 Inductive Inference from Noisy Examples: The Rule-Noise Dilemma and the Hybrid Finite State Filter (M. Gori, M. Maggini, G. Soda) 14:05 Inductive Learning in Symbolic Domains Using Structure- Driven Recurrent Neural Networks (A. Kuechler, C. Goller) 14:25 Neural Networks for the Classification of Structures (A. Sperduti) 14:45 - 15:15 Discussion 15:15 - 15:45 Break 15:45 - 16:25 INFERRING HIERARCHIES 15:45 Inferring Hierarchical Categories with ART-Based Modular Neural Networks (G. Bartfai) 16:05 A Tree-Structured Approach to Medical Diagnosis Tasks (J. Rahmel, P. Hahn) 16:25 - 16:45 Discussion 16:45 - 17:30 General Discussion and Closing DISCUSSION THEMES ----------------- In addition to discussions centered around the presentations, we want to foster an exchange of ideas and opinions about issues relevant for representing and processing structured knowledge with neural networks. 1. Are symbols ultimately necessary for knowledge, or are they an artefact? Can we provide symbol-less methods that achieve some kind of knowledge processing facility? With respect to the limited discussion time at the workshop, we would like to put the emphasis on the technical and practical aspects (experiments, methods), not so much on the underlying philosophical thoughts. 2. Why do we need structured knowledge? Because the world is structured? Because our cognition is systematic (Fodor & Pylyshyn's argument)? For efficiency reasons? And should structure be then explicitly represented? 3. Should we try to use neural networks for the representation and processing of structured knowledge, or are we simply wasting our time? After all, there are well-founded methods and techniques in traditional, symbol-oriented AI. If we should try, what are good reasons? o knowledge acquisition o learning, adaptability o generalization o performance o robustness o uncertainty o inconsistency o scalability o learning times o formal properties (correctness, completeness) o understandability o modularity 4. What are the characteristics of application domains/tasks where NN-models and methods are more suitable than other approaches (e.g. Inductive Logic Programming) when dealing with structured knowledge? 5. Learning and generalization on a structured domain -- what does this mean? Are there different levels of generalization capabilities, what can be achieved by NN models? 6. Are any of the approaches relevant for cognitive processes, e.g. memory, reasoning, language? 7. Is there evidence for the use of symbols in biological neural networks? When and where do symbols appear? 8. How difficult is it to build larger systems? They may consist of several NNSK modules, or constitute hybrid systems together with symbo-oriented modules. 9. Should we try to establish formal relations between neural methods and symbolic methods? An example might be Hoelldobler and Kalinke's or Pinkas' work. o equivalence o transformation o complexity 10. Should we try to model basic functions known from symbolic methods, or develop neural ones from scratch? Or is it like trying to build flying machines modeled after birds, instead of what we know as airplanes? An example: unification; is it necessary for reasoning system, or might a radically different approach be better? 11. What are the relations between knowledge-based methods from the fields of neural networks, machine learning, statistics? PARTICIPATION AND REGISTRATION ------------------------------ A number of places are available for those who wish to attend the workshop without doing an oral presentation. Potential attendees are requested to send a statement of interest to the Workshop Chair (franz@cis.njit.edu). Please note that attendees of workshops must register for the main ECAI conference. ORGANIZING COMMITTEE -------------------- Franz Kurfess (chair) New Jersey Institute of Technology, Newark, USA Daniel Memmi LEIBNIZ-IMAG, Grenoble, France Andreas Kuechler University of Ulm, Germany Arnaud Giacometti Universiti de Tours, France CONTACT ------- Prof. Franz Kurfess Computer and Information Sciences Dept. New Jersey Institute of Technology Newark, NJ 07102, U.S.A. Voice : +1/201-596-5767 Fax : +1/201-596-5767 E-mail: franz@cis.njit.edu PROGRAM COMMITTEE ----------------- Venkat Ajjanagadde - University of Minnesota, Minneapolis Ethem Alpaydin - Bogazici University Joan Cabestany - University of Catalunya Joachim Diederich - Queensland University of Technology Georg Dorffner - Universitaet Wien C. Lee Giles - NEC Research Institute Marco Gori - University of Florence Melanie Hilario - University of Geneva (co-chair) Steffen Hoelldobler - TU Dresden Mirek Kubat - University of Ottawa Wolfgang Maass - Technische Universitaet Graz Ernst Niebur - John Hopkins University Guenther Palm - University of Ulm Lokendra Shastri - International Computer Science Institute, Berkeley Hava Siegelman - Technion (Israeli Institue of Technology) Alessandro Sperduti - University of Pisa (co-chair) Chris J. Thornton - University of Sussex From juergen@idsia.ch Mon Jul 1 08:40:01 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id IAA12320 for ; Mon, 1 Jul 1996 08:39:55 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id IAA01587 for ; Mon, 1 Jul 1996 08:39:52 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA24332; Mon, 1 Jul 1996 18:35:19 +0800 Message-Id: <199607011035.SAA24332@cs.uwa.oz.au> From: juergen@idsia.ch (Juergen Schmidhuber) To: reinforce@cs.uwa.oz.au Subject: papers available [connectionists] Date: Thu, 27 Jun 96 20:53:27 +0200 3 related papers available, all based on a recent, novel, general reinforcement learning paradigm that allows for metalearning and incremental self-improvement (IS). ____________________________________________________________________ SIMPLE PRINCIPLES OF METALEARNING Juergen Schmidhuber & Jieyu Zhao & Marco Wiering Technical Report IDSIA-69-96, June 27, 1996 23 pages, 195 K compressed, 662 K uncompressed The goal of metalearning is to generate useful shifts of inductive bias by adapting the current learning strategy in a "useful" way. Our learner leads a single life during which actions are continually executed according to the system's internal state and current policy (a modifiable, probabilistic algorithm mapping environmental inputs and internal states to outputs and new internal states). An action is considered a learning algorithm if it can modify the policy. Effects of learning processes on later learning processes are measured using reward/time ratios. Occasional backtracking enforces success histories of still valid policy modifications corresponding to histories of lifelong reward accelerations. The principle allows for plugging in a wide variety of learning algorithms. In particular, it allows for embedding the learner's policy modification strategy within the policy itself (self-reference). To demonstrate the principle's feasibility in cases where traditional reinforcement learning fails, we test it in complex, non-Markovian, changing environments ("POMDPs"). One of the tasks involves more than 10^13 states, two learners that both cooperate and compete, and strongly delayed reinforcement signals (initially separated by more than 300,000 time steps). ____________________________________________________________________ A GENERAL METHOD FOR INCREMENTAL SELF-IMPROVEMENT AND MULTI-AGENT LEARNING IN UNRESTRICTED ENVIRONMENTS Juergen Schmidhuber To appear in X. Yao, editor, Evolutionary Computation: Theory and Applications. Scientific Publ. Co., Singapore, 1996 (based on "On learning how to learn learning strategies", TR FKI-198-94, TUM 1994). 30 pages, 146 K compressed, 386 K uncompressed. ____________________________________________________________________ INCREMENTAL SELF-IMPROVEMENT FOR LIFE- TIME MULTI-AGENT REINFORCEMENT LEARNING Jieyu Zhao Juergen Schmidhuber To appear in Proc. SAB'96, MIT Press, Cambridge MA, 1996. 10 pages, 107 K compressed, 429 K uncompressed. A spin-off paper of the TR above. It includes another experiment: a multi-agent system consis- ting of 3 co-evolving, IS-based animats chasing each other learns interesting, stochastic predator and prey strategies. (Another spin-off paper is: M. Wiering and J. Schmidhuber. Solving POMDPs using Levin search and EIRA. To be presented by MW at ML'96.) ____________________________________________________________________ To obtain copies, use ftp, or try the web: http://www.idsia.ch/~juergen/onlinepub.html FTP-host: ftp.idsia.ch FTP-filenames: /pub/juergen/meta.ps.gz /pub/juergen/ec96.ps.gz /pub/jieyu/sab96.ps.gz ____________________________________________________________________ Juergen Schmidhuber & Jieyu Zhao & Marco Wiering http://www.idsia.ch IDSIA From kbcs@konark.ncst.ernet.in Mon Jul 1 09:08:15 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA12548 for ; Mon, 1 Jul 1996 09:08:00 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA01878 for ; Mon, 1 Jul 1996 09:07:57 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA24311; Mon, 1 Jul 1996 18:33:23 +0800 Message-Id: <199607011033.SAA24311@cs.uwa.oz.au> From: KBCS Word Processing To: reinforce@cs.uwa.edu.au Subject: KBCS-96 (2nd CFP) Deadline Extended Date: Wed, 26 Jun 1996 18:53:29 +0500 (GMT) Second Call for Papers INTERNATIONAL CONFERENCE ON KNOWLEDGE BASED COMPUTER SYSTEMS National Centre for Software Technology Bombay, India December 16-18, 1996 THE DEADLINE FOR SUBMISSION OF PAPERS HAS NOW BEEN EXTENDED TO AUGUST 15, 1996 URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html ____________________________________________________________________________ The International Conference on Knowledge Based Computer Systems will be held in Bombay, India during December 16-18, 1996. The conference is intended to act as a forum for promoting interaction among researchers in the field of Artificial Intelligence in India and abroad. There will be a two day conference during December 16-17, 1996 followed by one day of post-conference tutorials on December 18, 1996. Papers are invited on substantial, original and unpublished research on all aspects of Artificial Intelligence, including, but not limited to the following: o AI Applications o AI Architectures o Artificial Life o Automatic Programming o Cognitive Modeling o Expert Systems o Foundations of AI o Genetic Algorithms o Information Retrieval o Intelligent Tutoring Systems o Knowledge Acquisition o Knowledge Representation o Machine Learning o Machine Translation o Natural Language Processing o Neural Networks o Planning and Scheduling o Reasoning o Robotics o Search Techniques o Speech Processing o Theorem Proving o Uncertainty Handling o User Interfaces o User Modeling o Vision Programme Committee: S. Arunkumar, IIT, Bombay Amitava Bagchi, IIM, Calcutta Pushpak Bhattacharya, IIT, Bombay Margaret A. Boden, U of Sussex, UK Nick Cercone, U of Regina, Canada B. B. Chaudhuri, ISI, Calcutta R. Chandrasekar, NCST, Bombay S. K. Goyal, GTE Labs , USA S. S. Gupta, TUL, Bombay J. R. Isaac, NIIT, New Delhi Aravind K. Joshi, R. A. Kowalski, Imperial College, UK U of Pennsylvania, USA H. N. Mahabala, INFOSYS, Bangalore M. Narasimha Murthy, IISc, Bangalore R. Narasimhan, CMC, Bangalore S. Ramani, NCST, Bombay (Chair) P. V. S. Rao, TIFR, Bombay Patrick Saint-Dizier, U of Paul Sabatier, France R. Sangal, IIT, Kanpur R. Uthurusamy, GMR, USA M. Vidyasagar, CAIR, Bangalore 2 Format of Submission: Authors should submit their papers, not to exceed 5000 words (including figures and references) either electronically or in hard copy. Papers should be in English. Papers should include an abstract of about 100-200 words in length. Papers outside the specified length are subject to rejection without review. Since reviewing will be "blind", the authors' names and affiliations along with the main area of the paper should be given only on a separate cover sheet. Hard copy submissions should be sent in triplicate. Papers in electronic form can be in any of the following formats: plain text, Postscript, Latex, Microsoft Word, or Wordstar. Submissions in electronic form are preferred. Send papers to the KBCS-96 Secretariat at the address below. Paper Submission Deadlines: o Papers due: August 15, 1996 o Acceptance Notification: October 15, 1996 o Camera Ready Copy due: December 1, 1996 Call for Tutorials: Proposals are invited for post-conference tutorials. Tutorials can be half-day or full-day, and will be held on December 18th, 1996. The proposal should be presented in the form of a 200-word abstract, one page topical outline of the content, description of the proposers and their qualifications relating to the tutorial content. Tutorial Submission Deadlines: o Proposal Submission: July 31, 1996 o Acceptance Notification: August 31, 1996 o Complete Tutorial materials due: December 1, 1996 Send proposals to the KBCS-96 Secretariat at the address below. Organizing Committee: George Arakal, NCST (Chair) K.S.R. Anjaneyulu, NCST P. Ravi Prakash, NCST Durgesh D. Rao, NCST M. Sasikumar, NCST T. Suresh, NCST For further information please refer to the KBCS-96 home page or write to the KBCS-96 Secretariat. ___________________________________________________________________________ Address KBCS-96 Secretariat Phone : +91 (22) 620 1606 National Centre for Software Technology Fax : +91 (22) 621 0139 Gulmohar Cross Rd No. 9 E-mail : kbcs@konark.ncst.ernet.in Juhu, Bombay 400 049, India URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html ---------------------------------------------------------------------------- From Claude.Touzet@VMESA12.U-3MRS.FR Mon Jul 1 09:26:37 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA12788 for ; Mon, 1 Jul 1996 09:26:27 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA02065 for ; Mon, 1 Jul 1996 09:26:21 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA24303; Mon, 1 Jul 1996 18:31:57 +0800 Message-Id: <199607011031.SAA24303@cs.uwa.oz.au> From: Claude.Touzet@VMESA12.U-3MRS.FR (Claude Touzet) To: EP-LIST@magenta.me.fau.edu, cogni-info@univ-lyon1.fr, neuropl@plearn.edu.pl, neur-sci@dl.ac.uk, enns-list@dcs.kcl.ac.uk, DAI-List@ece.sc.edu, dbworld@cs.wisc.edu, cells@tce.ing.uniroma1.it, reinforce@cs.uwa.edu.au Subject: CFP NEURAP'97 Date: Mon, 24 Jun 1996 17:18:08 +0200 My apologies if you receive multiple copies of this message. Please, post it. Claude Touzet, Email: Claude.Touzet@iuspim.u-3mrs.fr ************************************************************* NEURAP'97 Third International Conference on Neural Networks and their Applications IUSPIM, University of Aix-Marseille III, Marseilles, France, March 12-13-14, 1997 A forum for real world applications of artificial neural networks. A unique opportunity to share know-how and expertise between research and industry. Understanding why, how and when artificial neural networks are worth using. Understanding the structure of multidimensional data. What is the basic knowledge for artificial neural networks applications. How to compare neural networks and statistical tools and how to combine them for difficult problems. All the kinds of questions that will be addressed in the NEURAP'97 forum. 1997's main topic Data Analysis with artificial neural networks Remote sensing Time series Diagnosis Data mining Perception Multisensor fusion Sensor data analysis Finance ANN and statistical data analysis Other topics Applications, or methods, technics, tools that help to understand or develop neural networks applications Classification Fault tolerance Forecasting Hybrid systems (GA, fuzzy, symbolic representation, etc.) Knowledge acquisition Methods or tools for evaluating ANN performance Planning Pretreatement of the data Process control Simulation tools (research, education, development) Speech or image recognition etc. ... Conference Committee General Chair: Claude Touzet & Norbert Giambiasi, DIAM-IUSPIM (France) Program Chairs: Jacob Barhen, CESAR - Oak Ridge National Laboratory, TN, USA Jeanny Herault, LTIRF-INPG-ENSER de Grenoble, France Karl Goser, LBE - Universitat Dortmund, Germany Organisation Chair: Jean-Claude Bertrand, IUSPIM (France) Presentation To ensure a lively conference, all papers will be presented in plenary session (short presentations) and also through posters. However, to garantee the high quality of the presented works, the selection is based on full paper proposals. Depending on the maturity of the work presented, there will be short papers for on-going research of 4 pages long, and long papers for mature research results, up to 8 pages. All papers will be printed in full in the proceedings and must be in English. Deadlines and requirements Submissions are full length paper, not exceeding either four or eight A4 pages, double columns, 10-point font size. Please send 4 copies to the conference secretariat. Submission: December 16, 1996 Notification: February 3, 1997 Camera-Ready: February 20, 1997 NEURAP'97: March 12-13-14, 1997 Secretariat & information NEURAP'97 DIAM-IUSPIM , University of Aix-Marseille III, 13397 Marseille Cedex 20, France Tel.: ++ 33 91 05 60 60 Fax: ++ 33 91 05 60 33 Email: Claude.Touzet@iuspim.u-3mrs.fr URL: http://webiuspim.u-3mrs.fr/neurap97.html Registration fees (indicative) Registration before February 3, 1997: 1500 FF including three lunches (March 12, 13 & 14) 1100 FF without any lunch Registration after February 3, 1997: 1800 FF including three lunches (March 12, 13 & 14) 1400 FF without any lunch International Program Committee Jacob Bahren CESAR (Oak Ridge, USA) - President Karl Goser Universitat Dortmund (D) - President Jeanny Herault INPG (Grenoble, F) - President Frederic Alexandre CRIN-INRIA (Nancy, F) Gaston Baudat Sodeco (Geneve, CH) Jean-Marie Bernassau Sanofi Recherche (Montpellier, F) Pierre Bessiere IMAG/LIFIA (Grenoble, F) Jean Bigeon INPG (Grenoble, F) Giacomo Bisio Universita di Genova (I) Francois Blayo SAMOS (Paris, F) Jean Bourjault Universite de Besancon (F) Paul Bourret Onera-Cert (Toulouse, F) Joan Cabestany UPC (Barcelone, E) Mauricio Cirrincione Universita di Palerme (I) Ian Cloete University of Stellenbosch (SA) Philippe Coiffet CRIIF (Gif sur Yvette, F) Daniel Collobert CNET (lannion, F) Marie Cottrell Universite Paris I (F) Alexandru Cristea Institut of Virology (Bucharest, Romania) Dante Del Corso Politecnico di Torino (I) Pierre Demartines ICSI (Berkeley, USA) Marc Duranton LEP (Limeil-Brevannes, F) Kunihiko Fukushima Osaka University (J) Josef Goppert University of Tubingen (D) Mirta Gordon CEA (Grenoble, F) Marco Gori Universita di Firenze (I) Erwin Grosspietsch GMD (Sankt Augustin, D) Anne Guerin-Dugue INPG/LTIRF (Grenoble, F) John Hallam Dpt of Artificial Intelligence (Edinburgh, GB) Martin Hasler EPFL (Lausanne, CH) Jaap Hoekstra Delft University of Technology (NL) Masumi Ishikawa Kyushu Institute of Technology (J) Christian Jutten INPG (Grenoble, F) Juha Karhunen Helsinki University of Technology (FIN) Heinrich Klar Technische Universitat Berlin (D) Jean-Francois Lavignon DRET (Arcueil, F) John Lazzaro Univ. of California (Berkeley, USA) Vincent Lorquet ITMI (Grenoble, F) Ruy Milidiu University of Rio (Brasil) Fabien Moutarde Alcatel Alsthom Recherche (F) Alan F. Murray University of Edinburgh (GB) Akira Namatame National Defence Academy (J) Josef A. Nossek Technische Univ. Munchen (D) Erkki Oja Lappeenranta Univ. of Tech. (SF) Stanislaw Osowski University of Warsaw (Poland) Alberto Prieto Universidad de Granada (E) Pierre Puget CEA (Grenoble, F) Ulrich Ramacher Technische Universitat Dresden (D) Leornardo Reynieri Universita di Torino (I) Tamas Roska MTA-SZTAKI (Budapest, H) Juan Miguel Santos University of Buenos Aires (Argentina) Noel Sharkey University of Sheffield (GB) Leslie S. Smith University of Stirling (GB) John T. Taylor University College London (GB) Carme Torras Institut de Cibernetica/CSIC (E) Claude Touzet DIAM/IUSPIM (Marseille, F) Michel Verleysen UCL (Louvain-La-Neuve, B) Eric Vittoz CSEM (Neuchatel, CH) Alexandre Wallyn CGInn (Boulogne-Billancourt, F) From pazzani@super-pan.ICS.UCI.EDU Mon Jul 1 19:10:06 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id TAA21438 for ; Mon, 1 Jul 1996 19:09:59 -0500 Received: from paris.ics.uci.edu (paris.ics.uci.edu [128.195.1.50]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id TAA09835; Mon, 1 Jul 1996 19:09:53 -0500 Received: from super-pan.ics.uci.edu by paris.ics.uci.edu id aa21940; 1 Jul 96 12:19 PDT To: ML-LIST:; Subject: Machine Learning List: Vol. 8, No. 12 Reply-to: ml@ics.uci.edu Date: Mon, 01 Jul 1996 11:37:12 -0700 From: Michael Pazzani Message-ID: <9607011219.aa21940@paris.ics.uci.edu> Machine Learning List: Vol. 8, No. 12 Monday, July 1, 1996 Contents: Two new databases added to the UCI Repository CFP: Special Issue of Informatica on Data Mining Metrics Research Fellowships in Evolutionary Computing and Machine Learning Comments on "Test drive different algorithms on your problem" Re: Comments on "Test drive different algorithms on your problem" NEW BOOK: Robot Learning ECML-97: Call for Papers reminder/special issue of Machine Learning Call for Participation: Tainn'96 FOGA registration details: Pass the word! UAI-96 program and registration information SEAL'96 (2nd CFP) Proceedings of the HELNET Workshops on Neural Networks The Genetic Programming Notebook is now in Japanese SDAIR97 - Call for Papers ICONIP'97 Call for papers IDSIA papers available KBCS-96 (2nd CFP) Deadline Extended The Machine Learning List is moderated. Contributions should be relevant to the scientific study of machine learning. Mail contributions to ml@ics.uci.edu. Mail requests to be added or deleted to ml-request@ics.uci.edu. Back issues may be obtained from http://www.ics.uci.edu/AI/ML/Machine-Learning.html ---------------------------------------------------------------------- Subject: Two new databases added to the UCI Repository Date: Fri, 14 Jun 96 11:10:12 PDT From: ml-repos@ics.uci.edu The following databases were recently donated to the repository: 1. Abalone Database Donated by Sam Waugh Predicting the age of abalone from physical measurements Documentation: On everything 4177 instances, 8 attributes (one nominal) No missing attribute values 2. Census Income Database Donated by Ron Kohavi and Barry Becker Predicting whether income exceeds $50K/yr based on census data Documentation: On everything 48842 instances, 14 attributes (6 continuous and 8 nominal) Missing attribute values As a reminder, to access the repository either: 1. point your web browser to http://www.ics.uci.edu/~mlearn/MLRepository.html 2. ftp to ftp.ics.uci.edu, then cd to pub/machine-learning-databases Thanks to Sam Waugh, Ron Kohavi and Barry Becker for the donations! We are always looking for more databases. Anyone wishing to make a contribution may find donation directions on-line. Thank you, Chris Merz Repository Coordinator ------------------------------ Date: Wed, 12 Jun 1996 13:43:59 +1000 (EST) From: xindong@insect.sd.monash.edu.au Subject: CFP: Special Issue of Informatica on Data Mining Metrics CFP: A SPECIAL ISSUE OF INFORMATICA ON DATA MINING METRICS The development of a large number of rule induction and decision tree construction algorithms for data mining by researchers in machine learning and statistics, has seen empirical evaluation and justification become an important aspect for acceptance of newly developed algorithms by researchers in the field. To provide a comprehensive evaluation, we need a set of standard criteria such as: induction time, size of induction results, time to execute the induction results, and predicative accuracy. One algorithm may be able to perform better than others with one criterion, but may perform poorly with other criteria. With the same set of algorithms, we can also get different evaluation results from different sets of databases. The question of why, and under which circumstances one algorithm (whether it is newly designed or an existing one) outperforms others becomes more important than simply presenting empirical results from an arbitrarily selected set of databases. Research on data mining metrics is based on the above mentioned, widely adopted criteria. These metrics also look into the characteristics of the data sets for experiments such as: the numbers of classes, attributes and examples, the distribution of training examples in the example space, the level of noise and the mixture of continuous and nominal values. The aim is to develop a meaningful set of metrics with well documented experiment results for different algorithms. These metrics can be used as a testbed for newly developed algorithms against existing ones. Original papers are solicited that describe research in data mining metrics for a special issue in Informatica: An International Journal of Computing and Informatics. Topics include, but are not limited to, the following: - Development of data mining metrics - Different knowledge representations and their transformations in data mining - Generality and complexity of induction results - Pre-pruning and post-pruning - Deduction of inexact induction results - Artificial databases and real world databases: Which are more suitable for experimentation? - Top-down vs. bottom-up induction algorithms - Discretisation of real-valued attributes and fuzzification of symbolic values for data mining TIMETABLE Papers in 5 hard copies due: 12 August 1996 Acceptance Notification: 15 October 1996 Final papers in LaTeX: 15 November 1996 Publication: December 1996 GUEST EDITORS Dr Xindong Wu (xindong@insect.sd.monash.edu.au) Department of Software Development, Monash University 900 Dandenong Road, Caulfield East, Melbourne 3145, Australia URL: http://www.sd.monash.edu.au/~xindong/ Phone: +61 3 9903 1025 Fax: +61 3 9903 1077 Dr Matjaz Gams (matjaz.gams@ijs.si) Jozef Stefan Institute, Intelligent Systems Department Jamova 39, 61000 Ljubljana, Slovenia URL: http://www2.ijs.si/~mezi/matjaz.html Phone: +386 61 1773 900 Fax: +386 61 1258 058 ------------------------------ Date: Wed, 19 Jun 1996 17:37:33 +0000 From: Roger Miles Subject: Research Fellowships in Evolutionary Computing and Machine Learning The Intelligent Computer Systems Centre within the Faculty of Computer Studies and Mathematics undertakes strategic research and externally funded collaborative research projects. The Centre now wishes to appoint two Research Fellows and one Senior Research Fellow. The current areas of interest in the evolutionary computing and machine learning group are Genetic Algorithms, Classifier Systems, Artificial Life, Feature Section and Representation. It is hoped that the Fellows will work in matching or complementary areas. For the Research Fellow posts you will have a PhD and two years relevant experience in evolutionary computing and machine learning. For the Senior post you will have a significant publication record. The ability to liaise with industrial and foreign collaborators will be an advantage. The appointments will be in the range Reserarch Fellow: 13,834 - 18,196; Senior Research Fellow: 17,472- 22,568 depending on qualifications and experience. More information about ICSC can be found in http://www.btc.uwe.ac.uk For further information and an application form, to be returned by 9 July 1996, can be obtained from Personnel Services, UWE, Bristol, Frenchay Campus, Coldharbour Lane, BRISTOL BS16 1QY United Kingdom Telephone: +44 (0)117 976 3813 email: fay@btc.uwe.ac.uk Please quote reference number R/598. Informal enquiries about these posts can be made to Dr Roger Miles on +44 (0)117 976 3857 or by email at rgm@btc.uwe.ac.uk. ------------------------------ Date: Wed, 19 Jun 1996 08:56:35 -0400 From: Ibrahim Imam Subject: Comments on "Test drive different algorithms on your problem" By all means, It is neither my intention to defend nor to criticize the authors of these claims. I am just puzzled by the relevancy of some of these claims to the subject of discussion and the attempt to disprove or analyze some others. > Ronny Kohavi wrote: > Recently we have seen many claims (sometimes seemingly contradictory) such as: > > 1. Very simple classification rules perform well on most commonly > used datasets (Holte, 1993). I think, "SIMPLE" refers to the rules, not to the algorithm. I noticed that the author used the word "perform" which is confusing. > 2. There is no free lunch. No algorithm can perform no better than > any other on average if all targets are equiprobable (Wolpert, 1994). Does the part "if .." make any difference to the point of investigation? > 4. Generalization is a zero-sum enterprise; for every performance gain in > some subclass of learning situations there is an equal and > opposite effect in others (Schaffer, 1994). I guess running 17 hundred algorithm over 8 million datasets "may" create an argument against or for this theory. Also, attempting to disprove the theorem by an example (or argue against) is a waste of time. Just to explain myself, assume we start with a domain similar to the MONKs problems (2 decision classes; 432 possible examples). There are about 2^432 situations if "all examples were used for training". Also, we have to consider all possible combinations of different training and testing examples. For each combination, we have to run the experiment on all possible distributions of the training examples in the representation space. Finally, compare the average accuracy with 50%. > 5. "Rules are More than Trees" (Parsaye, slide title in the VLDB > summit,1996). The title sounds as if it is about representation issue rather than algorithms. Does this sentence refer to a knowledge representation issue? If so, it could be valid. If "More" refers to dynamic knowledge representation (declarative vs. procedural), Yes; to the applicability to different reasoning algorithms, Yes; the speed of making decisions, NO; ... > 9. Nearest neighbors are Bayes optimal. Asymptotically no algorithm > can do better (Fix and Hodges, 1951). Did the authors refer to Bayes algorithms only? Did the authors consider different generalization algorithms under their claim? > We have recently done an experiment comparing 17 algorithms on 8 large > datasets at the UC Irvine repository. The comparison is similar to > the StatLog comparison with two major differences: all datasets are at > UCI, and all algorithms can be trivially run from MLC++ by setting a > few environment variables. : Ibrahim F. Imam, SRA International, Inc. ------------------------------ Date: Sat, 22 Jun 1996 15:38:58 -0700 From: Ronny Kohavi Subject: Re: Comments on "Test drive different algorithms on your problem" Ibrahim> By all means, It is neither my intention to defend nor to Ibrahim> criticize the authors of these claims. I am just puzzled by Ibrahim> the relevancy of some of these claims to the subject of Ibrahim> discussion and the attempt to disprove or analyze some Ibrahim> others. My experience has been that people have heard these claims or slight variations and are surprised by their seemingly conflicting statements. Some of the claims are actually theorems, so clearly one would not try to disprove them with experiments. Some assumptions made in the theorems may not be very relevant in practice, and it is important to realize that. For example, the results of the paper show that simple rules have not performed well on the large datasets tested. >> 1. Very simple classification rules perform well on most commonly >> used datasets (Holte, 1993). Ibrahim> I think, "SIMPLE" refers to the rules, not to the Ibrahim> algorithm. I noticed that the author used the word "perform" Ibrahim> which is confusing. The author was indeed referring to the rules. The performance of simple rules in terms of accuracy can be measured. I am not clear why you think this is confusing. In fact, Rob Holte's 1R* algorithm is not even a proper induction algorithm because it looks at the test set. His goal was to show that simple rules are accurate and the results show that the absolute differences are not as big as some people might have expected (although these results apply mostly to small UC Irvine files that existed circa 1990). >> 2. There is no free lunch. No algorithm can perform no better than >> any other on average if all targets are equiprobable (Wolpert, >> 1994). Ibrahim> Does the part "if .." make any difference to the point Ibrahim> of investigation? This is a theorem and it's false without the "if" part. The relevance to the investigation is that although the theorem is interesting, real-world targets are unlikely to be coming from such a uniform distribution over the space of all targets. If the large UCI datasets tested represent an interesting distribution of targets, then for that distribution some algorithms described in the paper performed significantly better than others on average. >> 4. Generalization is a zero-sum enterprise; for every performance >> gain in some subclass of learning situations there is an equal and >> opposite effect in others (Schaffer, 1994). Ibrahim> I guess running 17 hundred algorithm over 8 million Ibrahim> datasets "may" create an argument against or for this theory. Under the conditions mentioned in the paper, this is a theorem not a theory. No attempt was be made to disprove it, but to question whether the underlying assumptions are reasonable. >> 5. "Rules are More than Trees" (Parsaye, slide title in the VLDB >> summit,1996). Ibrahim> The title sounds as if it is about representation issue Ibrahim> rather than algorithms. Does this sentence refer to a Ibrahim> knowledge representation issue? If so, it could be valid. OK, let me add a quotation from the previous slide in the abovementioned talk: "Trees can be expressed as simple rules. But rules are not trees---more general." 1. For discrete domains, this is total nonsense. Trees, rules, DNF, CNF (for binary domains), and many other forms are all equivalent in their representation power, i.e., they can all represent the same targets (although the representations may vary in size). For any reasonable representation (including trees and rules) most targets will have exponentially sized representation. This is a simple counting argument; there are 2^(2^n) Boolean functions, so if you can represent a structure in polynomially many bits, you can only represent 2^p(n) concepts. This talk resulted in a lot of discussions at the VLDB summit by people that thought one example of this that was given by Parsaye was very convincing. They thought they should be using rule induction systems and not decision-tree induction systems. My purpose was to show that (at least for the tested systems in the paper), the accuracy of rule induction systems is not necessarily higher. There may be other reasons for using rules related to comprehensibility, but the representation power issue is rather a weak reason. In fact, the segmentation power of decision trees and their ability to split large amounts of data into more manageable chunks may be very important in practice. 2. Assuming that continuous variables are thresholded, which is the most common representation used in rules (e.g., CN2, C4.5Rules), you're back to #1. As far as induction algorithms are concerned, we know of decision tree algorithms that are consistent under certain conditions (asymptotically optimal), but (at least to my knowledge) no similar proofs are known for any rule induction schemes. The nesting structure that decision trees provide is crucial for those proofs. >> 9. Nearest neighbors are Bayes optimal. Asymptotically no >> algorithm can do better (Fix and Hodges, 1951). Ibrahim> Did the authors refer to Bayes algorithms only? Did Ibrahim> the authors consider different generalization algorithms Ibrahim> under their claim? There may be some confusion between Bayesian networks with Bayesian optimality. The Bayes rule (which is Bayes optimal) refers to the case where the complete joint distribution of the labeled instances is known. The Bayes rule achieves the best possible accuracy by computing p(class | instance) and choosing the class with the highest posterior. There are theorems to show that nearest neighbor algorithms can be made asymptotically Bayes optimal by following a strategy where as the number of nearest neighbors used for classification grows at a slow rate (say log the number of instances). Ronny Kohavi (ronnyk@sgi.com, http://robotics.stanford.edu/~ronnyk) ------------------------------ Subject: NEW BOOK: Robot Learning Date: Thu, 27 Jun 96 10:46:22 EDT From: thrun+@heaven.learning.cs.cmu.edu I have the pleasure to announce the following book: **** Recent Advances in Robot Learning **** edited by Judy A. Franklin GTE Laboratories, Waltham, MA, USA Tom M. Mitchell Carnegie Mellon University, Pittsburgh, PA, USA Sebastian Thrun Carnegie Mellon University, Pittsburgh, PA, USA Reprinted from MACHINE LEARNING, 23:2-3 THE KLUWER INTERNATIONAL SERIES IN ENGINEERING AND COMPUTER SCIENCE VOLUME 368 Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. - Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. - Since robot learning involves decision making, there is an inherent active learning issue. - Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. - Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3). Kluwer Academic Publishers, Boston Date of publishing: June 1996 224 pp. Hardbound ISBN: 0-7923-9745-2 Prices: NLG: 175.00 USD: 94.00 GBP: 66.75 ============================================================================= CONTENTS o Real-World Robotics: Learning To Plan for Robust Execution, Scott W. Bennett, and Gerald F. DeJong o Robot Programming by Demonstration (RPD): Supporting the Induction, by Human Interaction, by Stefan Muench, Ruediger Dillmann, Siegfried Bocionek, and Michael Sassin o Performance Improvement of Robot Continuous-Path Operation through Iterative Learning Using Neural Networks, by Peter C.Y. Chen, James K. Mills, and Kenneth C. Smith o Learning Controllers for Industrial Robots, by C. Baroglio, A. Giordana, M. Kaiser, M. Nuttin, and R. Piola o Active Learning for Vision-Based Robot Grasping, by Marcos Salganicoff, Lyle H. Ungar, and Ruzena Bajcsy o Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning, by Minoru Asada, Shoichi Noda, Sukoya Tawaratsumita, and Koh Hosoda o Learning Operational Concepts from Sensor Data of a Mobile Robot, by Volker Klingspor, Katharina J. Morik, and Anke Rieger ============================================================================= See http://www.cs.cmu.edu/~thrun/papers/franklin.book.html for more information (paper abstracts, order form). ------------------------------ Date: Thu, 27 Jun 1996 12:17:58 +0200 From: Gerhard Widmer Subject: ECML-97: Call for Papers ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ECML-97 9th EUROPEAN CONFERENCE ON MACHINE LEARNING 23-26 April 1997, Prague, Czech Republic Call for Papers ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Up-to-date information on the conference can be found at http://is.vse.cz/ecml97/home.html ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ GENERAL INFORMATION: The 9th European Conference on Machine Learning (ECML-97) will be held in Prague, Czech Republic, during April 23-26, 1997, with informal workshops on April 26. The goal of ECML is to be a forum for the discussion of research in and applications of all forms of machine learning. Although the emphasis is on scientific advances in machine learning, ECML also requests papers on applications to practical problems or to other sciences, provided that general implications of the application are pointed out. One of the explicit goals of ECML-97 is to widen the audience and to strengthen relations between machine learning and other fields such as statistics, cognitive science, knowledge acquisition, linguistics, databases, etc. PROGRAM: The scientific program (April 23-25) will include invited talks, presentations of accepted papers, poster and demo sessions, as well as summary and commenting sessions on current and upcoming issues in machine learning. Saturday, April 26, will be devoted to informal workshops, for which a separate call for proposals will be published (contact Maarten van Someren (maarten@swi.psy.uva.nl) for details). RELEVANT RESEARCH AREAS: Submissions are invited in all areas of Machine Learning, including, but not limited to: abduction analogy applications of machine learning artificial neural networks case-based learning computational learning theory evolutionary computation inductive learning inductive logic programming knowledge base refinement knowledge discovery in databases knowledge-intensive learning language learning learning and problem solving models of human learning multi-agent learning multistrategy learning reinforcement learning revision and restructuring robot learning scientific discovery statistical approaches PROGRAM CHAIRS: Maarten van Someren (University of Amsterdam) and Gerhard Widmer (University of Vienna and Austrian Research Institute for Artificial Intelligence, Vienna). LOCAL CHAIR: Radim Jirousek (University of Economics, Prague). PROGRAM COMMITTEE: D. Aha (USA) F. Bergadano (Italy) I. Bratko (Slovenia) P. Brazdil (Portugal) K. De Jong (USA) L. De Raedt (Belgium) S. Dzeroski (Slovenia) W. Emde (Germany) Y. Kodratoff (France) N. Lavrac (Slovenia) R. Lopez de Mantaras (Spain) H. Mannila (Finland) S. Matwin (Canada) K. Morik (Germany) G. Nakhaeizadeh (Germany) C. Rouveirol (France) L. Saitta (Italy) J. Schmidhuber (Switzerland) D. Sleeman (UK) P. Vitanyi (Netherlands) S. Wrobel (Germany) SUBMISSION OF PAPERS: Two kinds of submissions are solicited: full papers describing substantial completed research or applications, and poster papers reporting on work in progress. Submissions must be clearly marked as one of these two kinds. The programme committee may decide to move accepted contributions from the full paper to the poster category. Full papers will be presented at plenary sessions and will appear in the conference proceedings, poster papers will be published in a technical report. The size limit for submissions is 12 pages for full papers, 5 pages for poster papers (excluding title page and bibliography, but including all tables and figures). Submissions exceeding this limit will not be reviewed! The conference proceedings will be published by Springer Verlag as part of the "Lecture Notes in AI (LNAI)" series. Submitted papers should preferably be formatted according to the LNAI guidelines (LaTeX style files are available at http://is.vse.cz/ecml97/home.html or by sending an e-mail to gerhard@ai.univie.ac.at). The publishers are also considering to make the proceedings available electronically, before the conference. A separate title page must contain the title of the paper, the names and addresses of all authors, up to three keywords, and an abstract of max. 200 words. The full address, including phone, fax and e-mail, must be given for the first author (or the contact person). The following items must be submitted by October 21, 1996: Four (4) hard copies of the paper, an electronic version (uuencoded, compressed PostScript) of the paper, and an electronic version of the titlepage only (plain ASCII). Send submissions, enquiries, etc. to: Gerhard Widmer (ECML-97) Austrian Research Institute for Artificial Intelligence, Schottengasse 3, A-1010 Vienna, Austria e-mail: gerhard@ai.univie.ac.at Papers will be evaluated with respect to relevance, technical soundness, significance, originality, and clarity. Papers reporting on real-world applications will be evaluated according to special criteria. A copy of the review form, which specifies the criteria to be used in the reviewing process, can be obtained electronically from http://is.vse.cz/ecml97/home.html. REGISTRATION AND FURTHER INFORMATION: For information about paper submission and program, contact the program chairs. For information about local arrangements, registration forms, etc. contact the local organizers at actionm@cuni.cz or check the ECML-97 WWW page. IMPORTANT DATES: Submission deadline: 21 October 1996 Notification of acceptance: 10 January 1997 Camera ready copy: 31 January 1997 Conference: 23-26 April 1997 IMPORTANT ADDRESSES: Submission of papers to: Gerhard Widmer (ECML-97) Austrian Research Institute for Artificial Intelligence, Schottengasse 3, A-1010 Vienna, Austria e-mail: gerhard@ai.univie.ac.at WWW site with conference and registration information, LaTeX style files, sample review form, etc.: http://is.vse.cz/ecml97/home.html E-mail address of local conference organization: actionm@cuni.cz ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Gerhard Widmer URL: http://www.ai.univie.ac.at/~gerhard Austrian Research Institute e-mail: gerhard@ai.univie.ac.at for Artificial Intelligence Schottengasse 3 tel: +43-1-53532810 A-1010 Vienna, Austria fax: +43-1-5320652 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ------------------------------ Date: Mon, 24 Jun 1996 00:26:04 -0700 From: Pat Langley Subject: reminder/special issue of Machine Learning This is the final call for submissions to Machine Learning for the special issue on "Learning with Probabilistic Representations", for which the deadline is July 1, 1996. In case you missed the earlier call, you can find it repeated in: http://robotics.stanford.edu/users/langley/special.html When formatting papers, please follow the instructions for authors given in: gopher://gopher.wkap.nl/00gopher_root1%3a%5bjournal.mach%5dmach.ifa including the constraint that paper length fall between 8,000 and 12,000 words, with full-page figures counting for 400 words. If you have questions prior to submission, please contact the editors of the special issue: Pat Langley (langley@cs.stanford.edu), Gregory Provan (provan@jupiter.risc.rockwell.com), and Padhraic Smyth (smyth@ics.uci.edu). ------------------------------ Date: Tue, 11 Jun 1996 14:33:41 +0400 (MEDT) From: Ethem Alpaydin Subject: Call for Participation: Tainn'96 Call for Participation TAINN'96, Istanbul 5th Turkish Symposium on Artificial Intelligence and Neural Networks To be held at Istanbul Technical University, Macka Campus June 27 - 28, 1996 Jointly-organized by Bogazici University and Istanbul Technical University Invited talk by Prof Teuvo Kohonen, Helsinki University of Technology Full program, registration and accommodation information can be e-received by Email: tainn96@boun.edu.tr URL: http://www.cmpe.boun.edu.tr/~tainn96 ------------------------------ Date: Thu, 13 Jun 1996 17:21:36 -0500 From: "Richard K. Belew" Subject: FOGA registration details: Pass the word! FOGA4 August 3-5, 1996 Unviersity of San Diego San Diego, California The 1996 Foundations of Genetic Algorithms (FOGA4) workshop will be the fourth biennial meeting of a workshop designed to explore theoretical issues relevant to genetic algorithms (GAs) and evolutionary compuation generally. FOGA4 will held Saturday August 3 through Monday, August 5, 199 at the Unviersity of San Diego in San Diego, California. Twenty-one excellent papers have been accepted for inclusion in this meeting, and these will be joined with three invited talks by: David Goldberg (Univ. Ill. Urbana-Champaign) William P. C. Stemmer ( Affymax Research Inst.) Umesh Vazirani (Univ. California - Berkeley) a wine reception and a lovely venue for what promises to be an excellent workshop. SPACE IS STRICTLY LIMITED, so register early if you are interested in attending (before 3 July to receive a discount). Enclosed below you will find: - Registration information - Registration form - A listing of talks/papers to be presented at the meeting This same information and subsequent details can (soon) be found at: http://www-cse.ucsd.edu/users/rik/foga96/foga96.html Let me know if you have any more questions. Rik Belew ================================================================ Foundations of Genetic Algorithms 1996 (FOGA-4 ) Univ. San Diego August 3 - 5, 1996 Registration information * The registration form below, together with a check (drawn on a U.S. bank) or money order for full payment should be mailed to: Michael D. Vose C.S. Dept., 107 Ayres Hall The University of Tennessee Knoxville, TN 37996 Attn: FOGA * Space for this workshop is VERY LIMITED and registrations will be accepted IN THE ORDER THEY ARE RECEIVED. You will receive Email confirmation as soon a possible, and written confirmation by mail before the meeting. * Housing for Friday, Saturday and Sunday nights have been arranged in pleasant apartments on the USD campus. These units are pairs of bedrooms with a shared living space, kitchenette and bathroom. You can reserve an entire bedroom (i.e., one half of the apartment) at the "single", below or share it ("double"). If you choose to double up and know who you'd like to share a room with, include this name on your registration. * The registration fee includes a wine reception Friday evening, snacks during the meeting and all meals from breakfast Saturday through lunch Monday EXCEPT FOR dinner Saturday night. (We have reserved this evening for people to go exploring San Diego's many restaurants.. A listing of our favorite San Diego restaurants will be available at the meeting.) * We will have vegetarian options for all meals, but please let us know if you have this or any other dietary restriction. * Also included in registration is the cost of a preprint of the book, and the cost of the book resulting from this meeting at a significant "attendees discount." * STUDENTS are eligible for a deeply discounted registration fee, subsidized by the Intl. Society for Genetic Algorithms. Students requesting this discount MUST provide a letter from their advisors on departmental letterhead stating that they are actively engaged in research in the area. Students will be housed in double rooms. * Since the USD rooms will be most convenient for FOGA participants and since USD charges a steep "commuter" fee for any conference participants NOT staying in USD rooms, we have made no provision for other accomodations. Commuters will be able to have lunch with us Saturday, Sunday and Monday. * Some additioal rooms can be had for days just before or just after our meeting. These will cost $35/day for doubles and $45/singles and must be arranged at the time of registration. These fees are for "room only" and do not include any meals. * Easy transport from and then back to the airport is available. (Eg, Cloud9 Shuttles quote $8 to USD campus; call 619-278-5841 for details). * USD is near the center of San Diego, but still quiet and green, on a hill overlooking the bay and downtown. (The final Presidential debate will be there shortly after we leave.) There are a number of good Mexican restaurants just down the hill (a short cab drive) in a section called Old Town. ================================================================ Foundations of Genetic Algorithms 1996 (FOGA-4 ) Univ. San Diego August 3 - 5, 1996 Registration form Last Name First Name Affiliation Contact info Email address Phone# Fax# Mailing Address City State ZIP Country Check ONE of the following: Early registration (<= 3 July 96) Single room $400 ____________ Double room 340 ____________ Commuters 250 ____________ Students 200 ____________ Registration ((> 3 July 96) Single room $450 ____________ Double room 400 ____________ Commuters 300 ____________ Students 250 ____________ If requesting STUDENT rates, is your advisor's letter enclosed? If requesting a double room, do you know someone you would like to room with? Do you require housing for additional days at USD? Number of days (Include $35 or $45/day.) Which days Dietary restrictions Other special requests (e.g., wheelchair accessible rooms) Send completed form to: Michael D. Vose C.S. Dept., 107 Ayres Hall The University of Tennessee Knoxville, TN 37996 ** INVITED LECTURES What should Genetic Algorithmists do? David Goldberg Univ. Ill. Urbana-Champaign Biological evolution as a model for genetic algorithms William P. C. Stemmer Affymax Research Inst. "Go with the Winners" Algorithms Umesh Vazirani Univ. California - Berkeley ** PRESENTED PAPERS Fitness Landscape Characterization by Between Variance of Decompositions (#1) Aizawa, Akiko Natl. Ctr. Sci. Info Sys., Japan Exact Uniform Initialization For Genetic Programming (#7) Bohm, Walter, A. Geyer-Schulz Vienna Univ. of Economics & Bus. Admin. Probing GA performance of fitness landscapes (#2) Bornholdt, Stefan Univ. Keil, Germany A Study of Fixed-Length Subset Recombination (#4) Crawford , Kelly , R. L. Wainwright, C. J. Hoelting, D. A. Schoenfeld Amoco On searching $\alpha$-ary Hypercubes and Related Graphs (#6) Culberson , Joseph , J. Lichtner Univ. Alberta, Canada Analyzing GAs Using Markov Models with Semantically Ordered States (#25) De Jong , Kenneth A. , W. M. Spears George Mason Univ. Convergence Controlled Variation (#13) Eshelman, Larry , K. Mathias, J. D. Schaffer Phillips Resarch Labs Fitness functions for multipleobjective optimization problems (#36) Greenwood, Garrison , X. Hu, J. G. D'Ambrosio West. Michigan Univ. Learning Linkage (#9) Harik, Georges Univ. Ill. Urbana-Champaign A Stationary Point Convergence Theory for Evolutionary Algorithms (#10) Hart, William Sandia Natl. Lab. Nonlinearity, Walsh Coefficients, Hyperplane Ranking and the Simple Genetic Algorithm (#24) Heckendorn, R. B. , D. Whitley, S. Rana Colorado State Univ. GAs (with sharing) in search, optimization and machine learning (#28) Horn, Jeffrey Univ. Ill. Urbana-Champaign Stochastic Context-Free Grammar Induction with a Genetic Algorithm Using Local Search (#27) Kammeyer, Thomas , R. K. Belew Univ. Calif. San Diego SEARCH, Blackbox Optimization, and Sample Complexity (#31) Kargupta, Hillol Los Alamos Natl. Lab. Diagonalizing the Simple GA Mixing Matrix (#42) Koehler, Gary Univ. Florida Replicators, Majorization and GAs: New models and analytic tools (#14) Menon, Anil , K. Mehrota, C. K. Mohan, S. Ranka Syracuse Univ. Noisy fitness evaluation in GAs and the dynamics of learning (#17) Rattray, Magnus Univ. Manchester, U.K. Genetic Algorithm Dynamics in Two-well Potentials with Basins and Barriers (#19) Shapiro , Jon Univ. Manchester, U.K. A formalism for real-parameter evolutionary algorithms and directed recombination (#16) Surry , Patrick , N. Radcliffe Quadstone Ltd., U.K. Further Results on the Markov Chain Model of GAs and Their Application to SA-like Strategy (#20) Suzuki , Joe Stanford Univ. A Search for Counterexamples to Two Conjectures on the Simple Genetic Algorithm (#22) Wright, Alden H. , G. Bidwell Univ. Montana ------------------------------ Date: Tue, 18 Jun 1996 16:56:42 -0700 (PDT) From: Eric Horvitz Subject: UAI-96 program and registration information ========================================================= P R O G R A M A N D R E G I S T R A T I O N ========================================================= THE TWELFTH ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE ** U A I 96 ** August 1-4, 1996 Reed College Portland, Oregon, USA ======================================= UAI www page at http://cuai-96.microsoft.com/ The effective handling of uncertainty is critical in designing, understanding, and evaluating computational systems tasked with making intelligent decisions. For over a decade, the Conference on Uncertainty in Artificial Intelligence (UAI) has served as a central meeting on advances in methods for reasoning under uncertainty in computer-based systems. The conference is the annual international forum for exchanging results on the use of principled uncertain-reasoning methods to solve difficult challenges in AI. Theoretical and empirical contributions first presented at UAI have continued to have significant influence on the direction and focus of the larger community of AI researchers. The scope of UAI covers a broad spectrum of approaches to automated reasoning and decision making under uncertainty. Contributions to the proceedings address topics that advance theoretical principles or provide insights through empirical study of applications. Interests include quantitative and qualitative approaches, and traditional as well as alternative paradigms of uncertain reasoning. Innovative applications of automated uncertain reasoning have spanned a broad spectrum of tasks and domains, including systems that make autonomous decisions and those designed to support human decision making through interactive use. * * * UAI 96 events include a full-day course on uncertain reasoning on the day before the main UAI 96 conference (Wednesday, July 31) at Reed College. Details on the course are available at: http://cuai-96.microsoft.com/tutor.htm * * * On Sunday, August 4, we will hold a UAI-KDD Special Joint Session on Learning, Probability, and Graphical Models at the Portland Convention Center. See information on the program below. * * * UAI-96 will begin shortly before KDD-96 (http://www-aig.jpl.nasa.gov/kdd96/), AAAI-96 (http://www.aaai.org/Conferences/National/1996/aaai96.html), and the AAAI workshops, and will be in close proximity to these meetings. * * * Refer to the UAI-96 WWW home page for late-breaking information: http://cuai-96.microsoft.com/ ======================================================================== ** UAI-96 Conference Program ** ======================================================================== ** Wednesday, July 31, 1996 ** Conference and Course Registration 8:00-8:30am Full-Day Course on Uncertain Reasoning 8:35-5:30pm (See: http://cuai-96.microsoft.com/ for course details) ================================================================ ** Thursday, August 1, 1996 ** Plenary Session I: Perspectives on Inference 8:45-10:15am Toward a Market Model for Bayesian Inference D. Pennock and M. Wellman A unifying framework for several probabilistic inference algorithms R. Dechter Computing upper and lower bounds on likelihoods in intractable networks T. Jaakkola and M. Jordan (Outstanding Student Paper Award) Query DAGs: A practical paradigm for implementing belief-network inference A. Darwiche and G. Provan Break 10:15-10:30am Plenary Session II: Applications of Uncertain Reasoning 10:30-12:00am MIDAS: An Influence Diagram for Management of Mildew in Winter Wheat A. Jensen and F. Jensen Optimal Factory Scheduling under Uncertainty using Stochastic Dominance A* P. Wurman and M. Wellman Supply Restoration in Power Distribution Systems --- A Case Study in Integrating Model-Based Diagnosis and Repair Planning S. Thiebaux, M. Cordier, O. Jehl, J. Krivine Network Engineering for Complex Belief Networks S. Mahoney and K. Laskey * Panel Discussion: "Reports from the front: Real-world experiences with uncertain reasoning systems" 12:00-12:45pm Moderator: B. D'Ambrosio Lunch 12:45-2:00pm Plenary Session III: Representation and Independence 2:00-3:40pm Context-Specific Independence in Bayesian Networks C. Boutilier, N. Friedman, M. Goldszmidt, D. Koller Binary Join Trees P. Shenoy Why is diagnosis using belief networks insensitive to imprecision in probabilities? M. Henrion, M. Pradhan, K. Huang, B. del Favero, G. Provan, P. O'Rorke On separation criterion and recovery algorithm for chain graphs M.n Studeny Poster Session I: Overview Presentations 3:40-4:00pm Poster Session I 4:00-6:00pm Inference Using Message Propagation and Topology Transformation in Vector Gaussian Continuous Networks S. Alag and A. Agogino Constraining Influence Diagram Structure by Generative Planning: An Application to the Optimization of Oil Spill Response J. Agosta An Alternative Markov Property for Chain Graphs S. Andersson, D. Madigan, and M. Perlman Object Recognition with Imperfect Perception and Redundant Description C. Barrouil and J. Lemaire A Sufficiently Fast Algorithm for Finding Close to Optimal Junction Trees A. Becker and D. Geiger Efficient Approximations for the Marginal Likelihood of Incomplete Data Given a Bayesian Network D. Chickering and D. Heckerman Independence with Lower and Upper Probabilities L. Chrisman Topological Parameters for Time-Space Tradeoff R. Dechter A Qualitative Markov Assumption and its Implications for Belief Change N. Friedman and J. Halpern A Probabilistic Model for Sensor Validation P. Ibarguengoytia and L. Sucar Bayesian Learning of Loglinear Models for Neural Connectivity K. Laskey and L. Martignon Geometric Implications of the Naive Bayes Assumption M. Peot Optimal Monte Carlo Estimation of Belief Network Inference M. Pradhan and P. Dagum On Coarsening and Feedback K. Reiser and Y. Chen A Discovery Algorithm for Directed Cyclic Graphs Thomas Richardson Efficient Enumeration of Instantiations in Bayesian Networks S. Srinivas and P. Nayak UAI-96 Meeting on Bayes Net Interchange Format 7:30-9:30pm (More information: http://cuai-96.microsoft.com/bnif.htm) ================================================================ ** Friday, August 2, 1996 Plenary Session IV: Time, Persistence, and Causality 8:45-10:15am A Structurally and Temporally Extended Bayesian Belief Network Model: Definitions, Properties, and Modelling Techniques C. Aliferis and G. Cooper Identifying independencies in causal graphs with feedback J. Pearl and R. Dechter Topics in Decision-Theoretic Troubleshooting: Repair and Experiment J. Breese and D. Heckerman A Polynomial-Time Algorithm for Deciding Equivalence of Directed Cyclic Graphical Models T. Richardson (Outstanding Student Paper Award) Break 10:15-10:30am Plenary Session V: Planning and Action under Uncertainty 10:30-12:00pm A Measure of Decision Flexibility R. Shachter and M. Mandelbaum A Graph-Theoretic Analysis of Information Value K. Poh and E. Horvitz Sound Abstraction of Probabilistic Actions in The Constraint Mass Assignment Framework A. Doan and P.Haddawy Flexible Policy Construction by Information Refinement M. Horsch and D. Poole * Panel Discussion: "Automated construction of models: Why, How, When?" 12:00-12:45pm Moderator: D. Koller Lunch 12:45-2:00pm Plenary Session VI: Qualitative Reasoning and Abstraction of Probability 2:00-3:30pm Generalized Qualitative Probability D. Lehmann Uncertain Inferences and Uncertain Conclusions H. Kyburg, Jr. Arguing for Decisions: A Qualitative Model of Decision Making B. Bonet and H. Geffner Defining Relative Likelihood in Partially Ordered Preferential Structures J. Halpern Poster Session II: Overview Presentations 3:40-4:00pm Poster Session II 4:00-6:00pm An Algorithm for Finding Minimum d-Separating Sets in Belief Networks S. Acid and L. de Campos Plan Development using Local Probabilistic Models E. Atkins, E. Durfee, K. Shin Entailment in Probability of Thresholded Generalizations D. Bamber Coping with the Limitations of Rational Inference in the Framework of Possibility Theory S. Benferhat, D. Dubois, H. Prade Decision-Analytic Approaches to Operational Decision Making: Application and Observation T. Chavez Learning Equivalence Classes of Bayesian Network Structures D. Chickering Propagation of 2-Monotone Lower Probabilities on an Undirected Graph L. Chrisman Quasi-Bayesian Strategies for Efficient Plan Generation: Application to the Planning to Observe Problem F. Cozman and E. Krotkov Some Experiments with Real-Time Decision Algorithms B. D'Ambrosio and S. Burgess An Evaluation of Structural Parameters for Probabilistic Reasoning: Results on Benchmark Circuits Y. El Fattah and R. Dechter Learning Bayesian Networks with Local Structure N. Friedman M. Goldszmidt Theoretical Foundations for Abstraction-Based Probabilistic Planning V. Ha and P. Haddawy Probabilistic Disjunctive Logic Programming L. Ngo A Framework for Decision-Theoretic Planning I: Combining the Situation Calculus, Conditional Plans, Probability and Utility D. Poole Coherent Knowledge Processing at Maximum Entropy by SPIRIT W. Roedder and C. Meyer Real-Time Estimation of Bayesian Networks R. Welch Testing Implication of Probabilistic Dependencies S.K.M. Wong UAI-96 Banquet and Invited Talk 7:30-9:30pm ================================================================ ** Saturday, August 3, 1996 ** Plenary Session VII: Developments in Belief and Possibility 8:45-10:00am Belief Revision in the Possibilistic Setting with Uncertain Inputs D. Dubois and H. Prade Approximations for Decision Making in the Dempster-Shafer Theory of Evidence M. Bauer Possible World Partition Sequences: A Unifying Framework for Uncertain Reasoning C. Teng Break 10:00-10:15am Plenary Session VIII: Learning and Uncertainty 10:15-11:45pm Asymptotic Model Selection for Directed Networks with Hidden Variables D. Geiger, D. Heckerman, C. Meek On the Sample Complexity of Learning Bayesian Networks N. Friedman and Z. Yakhini Learning Conventions in Multiagent Stochastic Domains using Likelihood Estimates C. Boutilier Critical Remarks on Single Link Search in Learning Belief Networks Y. Xiang, S.K.M Wong, N. Cercone * Panel Discussion: "Learning and Uncertainty: The Next Steps" 11:45-12:30pm Moderator: Greg Cooper Lunch 12:30-2:00pm Plenary Session IX: Advances in Approximate Inference 2:00-3:45pm Computational complexity reduction for BN2O networks using similarity of states A. Kozlov and J. Singh Sample-and-Accumulate Algorithms for Belief Updating in Bayes Networks E. Santos Jr., S. Shimony, E. Williams Tail Simulation in Bayesian Networks E. Castillo, C. Solares, P. Gomez Efficient Search-Based Inference for Noisy-OR Belief Networks: TopEpsilon K. Huang and M. Henrion Break 3:45-4:00pm * Panel Discussion: "UAI by 2005: Reflections on critical problems, directions, and likely achievements for the next decade" 4:00-5:00pm Moderator: E. Horvitz Report on the Bayes Net Interchange Format Meeting 5:00-5:20 UAI Planning Meeting 5:30-6:00 ================================================================ ** Sunday, August 4, 1996 ** UAI-KDD Special Joint Sessions Portland Convention Center Selected talks on learning graphical models from the UAI and KDD proceedings. UAI badges will be honored at the Portland Convention Center for the joint session. Plenary Session X: Learning, Probability, and Graphical Models I 8:30-12:00pm KDD: Knowledge Discovery and Data Mining: Toward a Unifying Framework U. Fayyad, G. Piatetsky-Shapiro, and P. Smyth UAI: Efficient Approximations for the Marginal Likelihood of Incomplete Data Given a Bayesian Network D. Chickering and D. Heckerman KDD: Clustering using Monte Carlo Cross-Validation P. Smyth UAI: Learning Equivalence Classes of Bayesian Network Structures D. Chickering Break 9:45-10:05am Plenary Session XI: Learning, Probability, and Graphical Models II 10:05-12:00pm UAI: Learning Bayesian Networks with Local Structure N. Friedman and M. Goldszmidt KDD: Rethinking the Learning of Belief Network Probabilities R. Musick UAI: Bayesian Learning of Loglinear Models for Neural Connectivity K. Laskey and L. Martignon KDD: Harnessing Graphical Structure in Markov Chain Monte Carlo Learning P. Stolorz ================================================================ Organization: ----------------- Program Cochairs: ================= Eric Horvitz Microsoft Research, 9S Redmond, WA 98052 Phone: (206) 936 2127 Fax: (206) 936 0502 Email: horvitz@microsoft.com WWW: http://www.research.microsoft.com/research/dtg/horvitz/ Finn Jensen Department of Mathematics and Computer Science Aalborg University Fredrik Bajers Vej 7,E DK-9220 Aalborg OE Denmark Phone: +45 98 15 85 22 (ext. 5024) Fax: +45 98 15 81 29 Email: fvj@iesd.auc.dk WWW: http://www.iesd.auc.dk/cgi-bin/photofinger?fvj General Conference Chair (General conference inquiries): ======================== Steve Hanks Department of Computer Science and Engineering, FR-35 University of Washington Seattle, WA 98195 Tel: (206) 543 4784 Fax: (206) 543 2969 Email: hanks@cs.washington.edu UAI Program Committee ====================== Fahiem Bacchus, University of Waterloo, Cananda Salem Benferhat, IRIT Universite Paul Sabatier, France Philippe Besnard, IRISA, France Mark Boddy, Honeywell Technology Center, USA Piero Bonissone, General Electric Research Laboratory, USA Craig Boutilier, University of British Columbia, Canada Jack Breese, Microsoft Research, USA Wray Buntine, Thinkbank, USA Luis M. de Campos, Universidad de Granada, Spain Enrique Castillo, Universidad de Cantabria, Spain Eugene Charniak, Brown University, USA Greg Cooper, University of Pittsburgh, USA Bruce D'Ambrosio, Oregon State University, USA Paul Dagum, Stanford University, USA Adnan Darwiche, Rockwell Science Center, USA Tom Dean, Brown University, USA Denise Draper, University of Washington, USA Marek Druzdzel, University of Pittsburgh, USA Didier Dubois, IRIT Universite Paul Sabatier, France Ward Edwards, University of Southern California, USA Kazuo Ezawa, AT&T Labs, USA Nir Friedman, Stanford University, USA Robert Fung, Prevision, USA Linda van der Gaag, Utrecht University, Netherlands Hector Geffner, Universidad Simon Bolivar, Venezuela Dan Geiger, Technion, Israel Lluis Godo, Campus Universitat Autonoma Barcelona, Spain Robert Goldman, Honeywell Technology Center, USA Moises Goldszmidt, SRI International, USA Adam Grove, NEC Research Institute, USA Peter Haddawy, University of Wisconsin-Milwaukee, USA Petr Hajek, Academy of Sciences, Czech Republic Joseph Halpern, IBM Almaden Research Center, USA Steve Hanks, University of Washington, USA Othar Hansson, Thinkbank, USA Peter Hart, Ricoh California Research Center, USA David Heckerman, Microsoft Research, USA Max Henrion, Lumina, USA Frank Jensen, Hugin Expert A/S, Denmark Michael Jordan, MIT, USA Leslie Pack Kaelbling, Brown University, USA Uffe Kjaerulff, Aalborg University, Denmark Daphne Koller, Stanford University, USA Paul Krause, Imperial Cancer Research Fund, UK Rudolf Kruse, University of Braunschweig, Germany Henry Kyburg, University of Rochester, USA Jerome Lang, IRIT Universite Paul Sabatier, France Kathryn Laskey, George Mason University, USA Paul Lehner, George Mason University, USA John Lemmer, Rome Laboratory, USA Tod Levitt, IET, USA Ramon Lopez de Mantaras, Spanish Scientific Research Council, Spain David Madigan, University of Washington, USA Christopher Meek, Carnegie Mellon University, USA Serafin Moral, Universidad de Granada, Spain Eric Neufeld, University of Saskatchewan, Canada Ann Nicholson, Monash University, Australia Ramesh Patil, Information Sciences Institute, USC, USA Judea Pearl, University of California, Los Angeles, USA Kim Leng Poh, National University of Singapore David Poole, University of British Columbia, Canada Henri Prade, IRIT Universite Paul Sabatier, France Greg Provan, Institute for Learning Systems, USA Enrique Ruspini, SRI International, USA Romano Scozzafava, Dip. Me.Mo.Mat., Rome, Italy Ross Shachter, Stanford University, USA Prakash Shenoy, University of Kansas, USA Philippe Smets, IRIDIA Universite libre de Bruxelles, Belgium David Spiegelhalter, Cambridge University, UK Peter Spirtes, Carnegie Mellon University, USA Milan Studeny, Academy of Sciences, Czech Republic Sampath Srinivas, Microsoft, USA Jaap Suermondt, Hewlett Packard Laboratories, USA Marco Valtorta, University of South Carolina, USA Michael Wellman, University of Michigan, USA Nic Wilson, Oxford Brookes University, UK Yang Xiang, University of Regina, Canada Hong Xu, IRIDIA Universite libre de Bruxelles, Belgium John Yen, Texas A&M University, USA Lian Wen Zhang, Hong Kong University of Science & Technology ============================================================== UAI-96 REGISTRATION FORM ============================================================== Please return this form via email to hanks@cs.washington.edu or use the web-based registration form available at the UAI-96 home page at http://cuai-96.microsoft.com to register online. ================================= Registrant Information ================================= Name: __________________________________ Affiliation: ____________________________ Address: ____________________________ ____________________________ ____________________________ Phone: ____________________________ Email address: ____________________________ ================================= Registration information ================================= ~~~~ Register me for the conference Non-student $275 Student $150 Students, please supply: Advisor's name and Email address: _______________________________________ ~~~~ Register me for the full-day course on uncertain reasoning (July 31) Non-student with conference registration $85 without conference registration $135 Student with conference registration $35 without conference registration $50 ================================= Dormitory accomodation ================================= Singles, doubles, and triples are available. All include a private bedroom; doubles and triples share a bathroom. Rates: Single $26.50 per night Double $21.50 per night Triple $16.50 per night ~~~~~~~~~~~~ Arrival date (earliest July 30) ~~~~~~~~~~~~ Departure date (latest August 4) I am paying for _____ people for _____ nights at a daily rate of _________ for a total of _________ ~~~~~~~~~~~~~~~~~~~~~~~ Sharing with (doubles and triples only) ~~~~~~~~~~~~~~~~~~~~~~~ Sharing with (triples only) =============================== Meal service =============================== Conference registration includes the conference banquet on August 2nd. Reed college offers a package of three lunches during the conference for a total of $24. ~~~~~~~~~~~~ Please register me for the lunch service ================================= Payment Summary ================================= $______________ Conference registration $______________ Full-day course registration $______________ Lodging charges $______________ Meal charges $______________ TOTAL AMOUNT ~~~~~~~~~~ Please charge my ____ Visa ____ MasterCard ~~~~~~~~~~~~~~~~~~~ Card Number ~~~~~~~~~~~~~~~~~~~ Expiration date ~~~~~~~~~ I will send a check via surface mail. Address for checks: Steve Hanks Department of Computer Science and Engineering University of Washington Box 352350 Seattle, WA 98195-2350 ~~~~~~~~~ I will pay at the conference ====================================================================== For questions about arrangements and registration issues, contact the Steve Hanks (hanks@cs.washington.edu). For questions about the program, contact Eric Horvitz (horvitz@microsoft.com) or Finn Jensen (fvj@iesd.auc.dk). ====================================================================== ------------------------------ From: Hyun Myung Subject: SEAL'96 (2nd CFP) Date: Wed, 19 Jun 1996 15:58:05 +1000 (KDT) * S E C O N D C A L L F O R P A P E R S * The First Asia-Pacific Conference on Simulated Evolution And Learning (SEAL'96) Taejon, Korea 9-12 November 1996 in conjunction with Micro-Robot World Cup Soccer Tournament (MIROSOT'96) WWW for SEAL'96: URL: http://vivaldi.kaist.ac.kr/~seal96/ URL: http://www.cs.adfa.oz.au/~xin/conference_cfps/seal96_cfps.html ------------------------------ Date: Thu, 20 Jun 1996 13:04:27 -0700 From: "Marcel J. van der Heyden" Subject: Proceedings of the HELNET Workshops on Neural Networks HELNET International Workshop on Neural Networks Proceedings Volume I/II (1994/1995) M.J. van der Heyden, J. Mrsic-Floegel and K. Weigl (eds) ** http://www.leidenuniv.nl/medfac/fff/groepc/chaos/helnet/ ** The HELNET workshops are informal meetings primarily targeted towards young researchers from neural networks and related fields. They are traditionally organised a few days prior to the ICANN conferences. Participants are offered the opportunity to present and extensively discuss their work as well as more general topics from the neural network field. In the HELNET proceedings a large variety of topics is treated: from the formal description of networks to neurobiology - from conceptual viewpoints to commercial applications. Thus, this collection of papers gives a comprehensive overview of current and ongoing research on neural networks. The proceedings can be browsed on-line at: http://www.leidenuniv.nl/medfac/fff/groepc/chaos/helnet/ On-line ordering is also provided for using credit card details or having an invoice sent. Table of Contents: Development of Spatio-Temporal Receptive Fields for Motion Detection in a Linsker Type Model (S. Wimbauer, W. Gerstner and J.L. van Hemmen) The Dependence on Size and Calcium Dynamics of Motoneuron Firing Properties: A Model Study (Marcel J. van der Heyden, A.A.J. Hilgevoord and L.J. Bour) Annealing in Minimal Free Energy Vector Quantization (D.R. Dersch and P. Tavan) Projection Learning: A Critical Review of Practical Aspects (Konrad Weigl) Transforming Hard Problems into Linearly Separable ones with Incremental Radial Basis Function Networks (B. Fritzke) Why are Neural Nets not Intelligent? (Harald Huening) Aspects of Information Detection using Entropy (Janko Mrsic-Floegel) Generating a Fractal Image by Programmed Cell Death: a Biological Communication Strategy for Parallel Computers (David W.N. Sharp) The Impossibility to Localize Electrical Activity in the Brain from EEG-Recordings by Means of Artificial Neural Networks (Sylvia C. Pont and Bob W. van Dijk) Analysis of Electronic Circuits with Evolutionary Strategies (Harald Gerlach and Joerg D. Becker) Neural Networks and Statistics: A Brief Overview (Marcel J. van der Heyden) Self-Controlling Chaos in Neuromodules (Nico Stollenwerk) The Effects of Feature Selection on Backpropagation in Feed-Forward Neural Networks (Selwyn Piramuthu) Exploring the Role of Emotion in the Design of Autonomous Systems (Raju S. Bapi) A Fusion of Game-Theory Based Learning and Projection Learning for Image Classification (Konrad Weigl and Shan Yu) Codierung eines Problems in die Sprache der Evolution (Harald Gerlach) Modelling the Wiener Cascade Using Time Delayed and Recurrent Neural Networks (M.G. Wagner, I.M. Thompson, S. Manchanda, P.G. Hearne and G.R.R. Greene) Niche memories for Temporal Sequence Processing: learning, recognition and tracking using neural representations (Janko Mrsic-Floegel) Stretching the Limits of Learning Without Modules (Antal van den Bosch and Ton Weijters) The Future for Weightless Systems (Nick Bradshaw) A Way to Improve Error Correction Capability of Hopfield Associative Memory in the Case of Saturation (Dmitry O. Gorodnichy) ------------------------------ Date: Sun, 23 Jun 1996 14:54:10 -0500 From: Jaime Fernandez Subject: The Genetic Programming Notebook is now in Japanese The Genetic Programming Notebook is now in Japanese and English. Soon it will also be in Spanish. It is located at: http://www.jrabbit.com/~jjf/gp If you have any problems with that address you can try on of the mirrors at: http://www.jjf.com/gp http://holgate.jsc.nasa.gov/~jjf/gp http://tommy.jsc.nasa.gov/~jjf/gp/ http://www.owlnet.rice.edu/~jjf/gp/ http://www.metricanet.com/~jjf/gp http://www.mysite.com/jjf/gp The Genetic Programming Notebook contains information on the following categories: Genetic Programming GP Tutorial Software People Other Sites Research Groups Misc Bibliographies Papers Journals FAQ Calls for Papers Conferences Commercial Genetic Algorithms Genetic Algorithms Software People Other Sites Research Groups Misc Bibliographies Papers Journals FAQ Courses Parallel Repositories Tutorials Artificial Intelligence & Robotics Artificial Intelligence FAQs Newsgroups Machine Learning Artificial life Sites Fuzzy Logic Neural Nets Robots Financial Programming I want to thank FUJITA TATSUYA for his help in the translation. WWW : http://surgeonc.csse.muroran-it.ac.jp/~fujita/FUJITAN2.html Jaime J. Fernandez Jr. | Email: jjf@jjf.com Metrica, Inc. | WWW: http://www.jjf.com castles pages: http://www.jrabbit.com/~jjf/castles http://www.owlnet.rice.edu/~jjf/castles ------------------------------ Subject: SDAIR97 - Call for Papers Date: Mon, 24 Jun 1996 16:57:32 -0700 From: Frank Jenkins Call for Papers SDAIR '97 Sixth Annual Symposium on Document Analysis and Information Retrieval April 20-23, 1997 Alexis Park Resort, Las Vegas, Nevada SPONSOR Information Science Research Institute University of Nevada, Las Vegas SYMPOSIUM CHAIR Jan O. Pedersen Xerox Palo Alto Research Center pedersen@parc.xerox.com PROGRAM CHAIRS Document Analysis: Hiromichi Fujisawa Hitachi Central Research Lab fujisawa@crl.hitachi.co.jp Information Retrieval: Susan Dumais Bellcore std@bellcore.com SYMPOSIUM SECRETARY Patty Corhn University of Nevada, Las Vegas Information Science Research Institute 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 (702)895-3338 (702)895-1183 (fax) sdair@isri.unlv.edu SCOPE The purpose of this symposium is to present results of state-of-the-art research and to encourage the exchange of ideas in the general field of automatic extraction of information from images of printed documents. Papers are solicited on all aspects of document image analysis and information retrieval, both theoretical and applied, with particular emphasis on: Document Analysis: High-Accuracy Transcription Postprocessing of OCR Results Keyword Search in Textual Images Multilingual OCR, Language ID, etc. Geometric and Logical Layout Analysis Recognition of Forms, Tables and Equations Models of Document Image Degradation Methods for Performance Evaluation Information Retrieval: Full-Text Retrieval Retrieval from OCR'ed Text Image and Multimedia Retrieval Text Categorization Multilingual Retrieval User Interaction and Interfaces Text Representation Retrieval from Structured Documents Evaluation of IR Systems Papers on subjects in the intersection of these two areas will be given priority. SUBMISSIONS Please send five copies of complete papers, with the corresponding author's name, postal address, telephone and fax numbers and e-mail address, to the appropriate Chair: Hiromichi Fujisawa, Chair (Document Analysis) c/o Information Science Research Institute University of Nevada, Las Vegas 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 Susan Dumais, Chair (Info. Retrieval) c/o Information Science Research Institute University of Nevada, Las Vegas 4505 Maryland Parkway Box 454021 Las Vegas, NV 89154-4021 Manuscripts should be no longer than 20 double-spaced pages or 5,000 words and should not already have been accepted for publication by another conference or journal, nor should they be submitted elsewhere during the SDAIR'97 review period. Manuscripts must arrive on or before the due date. Both camera-ready paper and machine-readable source copies of accepted papers will be required. The proceedings will be available at the conference. Student papers are encouraged. The symposium will present a prize for the best accepted student paper. CONFERENCE TIMETABLE Papers Due September 30, 1996 Notification To Authors December 2, 1996 Camera Ready and Machine Readable Copy January 15, 1997 DOCUMENT ANALYSIS COMMITTEE: Hiromichi FUJISAWA, chair, Hitachi Central Research Lab Andreas DENGEL, German Research Center for Artificial Intelligence Tin Kam HO, Bell Laboratories Jonathan J. HULL, Ricoh California Research Center Junichi KANAI, University of Nevada, Las Vegas Seong Whan LEE, Korea University Yasuaki NAKANO, Shinshu University Larry SPITZ, Daimler Benz Research & Technical Center Suzanne TAYLOR, Lockheed Martin Karl TOMBRE, INRIA Lorraine INFORMATION RETRIEVAL COMMITTEE: Susan DUMAIS, Chair, Bellcore Robert ALLEN, Bellcore Abe BOOKSTEIN, University of Chicago Jamie CALLAN, University of Massachusetts Stephen GALLANT, Belmont Research Donna HARMAN, National Institute of Standards and Technology David HULL, Rank Xerox Research Center Kazem TAGHVA, Univ of Nevada, Las Vegas Peter SCHAUBLE, Swiss Federal Institute of Technology, Zurich Ellen VOORHEES, National Institute of Standards and Technology Ross WILKENSON, Royal Melbourne Institute of Technology ------------------------------ From: Nikola Kasabov Date: Wed, 19 Jun 1996 14:28:43 -1200 Subject: ICONIP'97 Call for papers ICONIP'97 jointly with ANZIIS'97 and ANNES'97 The Fourth International Conference on Neural Information Processing-- The Annual Conference of the Asian Pacific Neural Network Assembly, jointly with The Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems, and The Third New Zealand International Conference on Artificial Neural Networks and Expert Systems 24-28 November, 1997 Dunedin/Queenstown, New Zealand In 1997, the annual conference of the Asian Pacific Neural Network Assembly, ICONIP'97, will be held jointly with two other major international conferences in the Asian Pacific Region, the Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems (ANZIIS'97) and the Third New Zealand International Conference on Artificial Neural Networks and Expert Systems (ANNES'97), from 24 to 28 November 1997 in Dunedin and Queenstown, New Zealand. The joint conference will have three parallel streams: Stream1: Neural Information Processing Stream2: Computational Intelligence and Soft Computing Stream3: Intelligent Information Systems and their Applications TOPICS OF INTEREST Stream1: Neural Information Processing * Neurobiological systems * Cognition * Cognitive models of the brain * Dynamical modelling, chaotic processes in the brain * Brain computers, biological computers * Consciousness, awareness, attention * Adaptive biological systems * Modelling emotions * Perception, vision * Learning languages * Evolution Stream2: Computational Intelligence and Soft Computing * Artificial neural networks: models, architectures, algorithms * Fuzzy systems * Evolutionary programming and genetic algorithms * Artificial life * Distributed AI systems, agent-based systems * Soft computing--paradigms, methods, tools * Approximate reasoning * Probabilistic and statistical methods * Software tools, hardware implementation Stream3: Intelligent Information Systems and their Applications * Connectionist-based information systems * Hybrid systems * Expert systems * Adaptive systems * Machine learning, data mining and intelligent databases * Pattern recognition and image processing * Speech recognition and language processing * Intelligent information retrieval systems * Human-computer interfaces * Time-series prediction * Control * Diagnosis * Optimisation * Application of intelligent information technologies in: manufacturing, process control, quality testing, finance, economics, marketing, management, banking, agriculture, environment protection, medicine, geographic information systems, government, law, education, and sport * Intelligent information technologies on the global networks HONORARY CHAIR Shun-Ichi Amari, Tokyo University GENERAL CONFERENCE CHAIR Nikola Kasabov, University of Otago INTERNATIONAL ADVISORY COMMITTEE (TENTATIVE) D Aha (USA), M H Ang (Singapore), I Aleksander (UK), J Andreae (NZ), P Andreae (NZ), S Amari (Japan), M Arbib (USA), Y Attikiouzel (AUS), J Austin (UK), S Bang (Korea), J Bezdek (USA), A Bulsara (USA), Z Boger (Israel), T Caelli (AUS), T Chen (China), G Coghill (NZ), T Cohen (NZ), G Deboeck (USA), Fr Esteva (Spain), M Fedrizzi (Italy), D Fogel (USA), T Gedeon (AUS), P Goodman (USA), D Fillev (USA), H C Fu (Taiwan), T Fukuda (Japan), K Fukushima (Japan), T Furuhashi (Japan), J van den Herik (NL), K Hirota (Japan), R Hodgson (NZ), M Jabri (AUS), L Jain (AUS), M Jamshidi (USA), S Jones (UK), J Kacprzyk (Poland), M Kawato (Japan), L Koczy (Hungary), T Kohonen (Finland), D Lakof (Bulgaria), M Lim (Singapore), R MarksII (USA), A Mason (NZ), G Matsumoto (Japan), I Mitchell (NZ), N Morgan (USA), N McNaughton (NZ), R O'Shea (NZ), G Pasi(Italy), L Patnaik (India), D Pham (UK), M Purvis (NZ), A Ralescu (USA), K Reinartz (Germany), Y Sagisaka (Japan), P Sallis (NZ), E Sanches (France), N Sharkey (UK), R Sun (USA), H Szu (USA), J Taylor (UK), P Treleavan (UK), D Tuck (NZ), G Vachkov (Bulgaria), V Vemuri (USA), I Witten (NZ), Y Wu (China), L Xu (Hong Kong), T Yamakawa (Japan), Y Yamazaki (Japan), W Yeap (NZ), D Yun (Hawaii), L Zadeh (USA), J Zurada (USA) LOCAL ORGANIZING COMMITTEE: Philip Sallis (Chairperson), Nikola Kasabov, Kitty Ko, Louise Vink, Ian Smith, Lyall McLean, Ron Heath, Wai-kiang Yeap, Anthony Robins, Robert O'Shea, Peter Norris, University of Otago CONFERENCE ORGANISER Ms Kitty Ko Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand phone: +64 3 479 8153, fax: +64 3 479 8311, email: kittyko@commerce.otago.ac.nz CALL FOR PAPERS Papers must be received by 30 May 1997. They will be reviewed by senior researchers in the field and the authors will be informed about the decision of the review process by 20 July 1997. The accepted papers must be submitted in a camera-ready format by 20 August. All accepted papers will be published by IEEE Computer Society Press. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialised audience. Papers will be presented at the conference either in an oral or in a poster session. Please submit three copies of the paper written in English on A4-format white paper with one inch margins on all four sides, in two column format, on not more than 4 pages, single-spaced, in Times or similar font of 10 points, and printed on one side of the page only. Centred at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by an abstract and the text. In the covering letter the stream and the topic of the paper according to the list above should be indicated. The IEEE Transaction journals LaTex article style can be used. SPECIAL ISSUES OF JOURNALS AND EDITED VOLUMES Selected papers will be published in special issues of scientific journals. The organising committee is looking for publications of edited volumes which include chapters covering the conference topics written by invited conference participants. TUTORIALS (24 November) Conference tutorials will be organized to introduce the basics of cognitive modelling, dynamical systems, neural networks, fuzzy systems, evolutionary programming, soft computing, expert systems, hybrid systems, and adaptive systems. Proposals for tutorials are due on 30 May 1997. EXHIBITION Companies and university research laboratories are encouraged to exhibit their developed or distributing software and hardware systems. STUDENT SESSION Postgraduate students are encouraged to submit papers to this session following the same formal requirements for paper submission. The submitted papers will be published in a separate brochure. SPECIAL EVENTS FOR PRACTITIONERS The New Zealand Computer Society is organising special demonstrations, lectures and materials for practitioners working in the area of information technologies. VENUE (Dunedin/Queenstown) The Conference will be held at the University of Otago, Dunedin, New Zealand. The closing session will be held on Friday, 28 November on a cruise on one of the most beautiful lakes in the world, Lake Wakatipu. The cruise departs from the famous tourist centre Queenstown, about 300 km from Dunedin. Transportation will be provided and there will be a separate discount cost for the cruise. ACCOMMODATION Accommodation has been booked at St Margaret's College located right on the Campus and 10 minutes from downtown Dunedin. The College offers well equipped facilities including library, sport hall, music hall and computers with e-mail connection. Full board (NZ$50) is available during the conference days as well as two days before and after the conference. Accommodation is also available for a range of hotels in the city. TRAVELLING The Dunedin branch of House of Travel, a travelling company, is happy to assist in any domestic and international travelling arrangements for the Conference delegates. They can be contacted through email: travel@es.co.nz, fax: +64 3 477 3806, phone: +64 3 477 3464, or toll free number: 0800 735 737 (within NZ). POSTCONFERENCE EVENTS Following the closing conference cruise, delegates may like to experience the delights of Queenstown, Central Otago, and Fiordland. Travel plans can be coordinated by the Dunedin Visitor Centre (phone: +64 3 474 3300, fax: +64 3 474 3311). IMPORTANT DATES Papers due: 30 May 1997 Proposals for tutorials: 30 May 1997 Notification of acceptance: 20 July 1997 Final camera-ready papers due: 20 August 1997 Registration of at least one author of a paper: 20 August 1997 Early registration: 20 August 1997 CONFERENCE CONTACTS, PAPER SUBMISSIONS, CONFERENCE INFORMATION, REGISTRATION FORMS Conference Secretariat Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand; phone: +64 3 479 8142; fax: +64 3 479 8311; email: iconip97@otago.ac.nz Home page: http://divcom.otago.ac.nz:800/com/infosci/kel/conferen.htm ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ICONIP'97 jointly with ANZIIS'97 and ANNES'97 TENTATIVE REGISTRATION PLEASE PRINT Title:________________________________ Surname:______________________________ First Name:___________________________ Position:_____________________________ Organisation:_________________________ Department:___________________________ Address:______________________________ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ City:_________________________________ Country:______________________________ Phone:________________________________ Fax:__________________________________ Email:________________________________ Yes/No. Would you attend the conference? Yes/No. Would you submit a paper? Yes/No. Would you attend the closing session on the cruise? Yes/No. Would you like any further information? Please mail a copy of this completed form to: Ms Kitty Ko Department of Information Science University of Otago PO Box 56 Dunedin New Zealand. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Assoc.Professor Dr Nikola Kasabov phone:+64 3 479 8319 Director of Graduate Studies fax:+64 3 479 8311 Department of Information Science nkasabov@otago.ac.nz University of Otago P.O. Box 56, Dunedin, New Zealand home page http://divcom.otago.ac.nz:800/COM/INFOSCI/KEL/home.htm ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ------------------------------ Date: Thu, 27 Jun 96 20:54:50 +0200 From: Juergen Schmidhuber Subject: IDSIA papers available 3 related papers available, all based on a recent, novel, general reinforcement learning paradigm that allows for metalearning and incremental self-improvement (IS). ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ SIMPLE PRINCIPLES OF METALEARNING Juergen Schmidhuber & Jieyu Zhao & Marco Wiering Technical Report IDSIA-69-96, June 27, 1996 23 pages, 195 K compressed, 662 K uncompressed The goal of metalearning is to generate useful shifts of inductive bias by adapting the current learning strategy in a "useful" way. Our learner leads a single life during which actions are continually executed according to the system's internal state and current policy (a modifiable, probabilistic algorithm mapping environmental inputs and internal states to outputs and new internal states). An action is considered a learning algorithm if it can modify the policy. Effects of learning processes on later learning processes are measured using reward/time ratios. Occasional backtracking enforces success histories of still valid policy modifications corresponding to histories of lifelong reward accelerations. The principle allows for plugging in a wide variety of learning algorithms. In particular, it allows for embedding the learner's policy modification strategy within the policy itself (self-reference). To demonstrate the principle's feasibility in cases where traditional reinforcement learning fails, we test it in complex, non-Markovian, changing environments ("POMDPs"). One of the tasks involves more than 10^13 states, two learners that both cooperate and compete, and strongly delayed reinforcement signals (initially separated by more than 300,000 time steps). ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ A GENERAL METHOD FOR INCREMENTAL SELF-IMPROVEMENT AND MULTI-AGENT LEARNING IN UNRESTRICTED ENVIRONMENTS Juergen Schmidhuber To appear in X. Yao, editor, Evolutionary Computation: Theory and Applications. Scientific Publ. Co., Singapore, 1996 (based on "On learning how to learn learning strategies", TR FKI-198-94, TUM 1994). 30 pages, 146 K compressed, 386 K uncompressed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ INCREMENTAL SELF-IMPROVEMENT FOR LIFE- TIME MULTI-AGENT REINFORCEMENT LEARNING Jieyu Zhao Juergen Schmidhuber To appear in Proc. SAB'96, MIT Press, Cambridge MA, 1996. 10 pages, 107 K compressed, 429 K uncompressed. A spin-off paper of the TR above. It includes another experiment: a multi-agent system consis- ting of 3 co-evolving, IS-based animats chasing each other learns interesting, stochastic predator and prey strategies. (Another spin-off paper is: M. Wiering and J. Schmidhuber. Solving POMDPs using Levin search and EIRA. To be presented by MW at ML'96.) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ To obtain copies, use ftp, or try the web: http://www.idsia.ch/~juergen/onlinepub.html FTP-host: ftp.idsia.ch FTP-filenames: /pub/juergen/meta.ps.gz /pub/juergen/ec96.ps.gz /pub/jieyu/sab96.ps.gz ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Juergen Schmidhuber & Jieyu Zhao & Marco Wiering http://www.idsia.ch IDSIA ------------------------------ Date: Wed, 26 Jun 1996 18:53:28 +0500 (GMT) From: KBCS Word Processing Subject: KBCS-96 (2nd CFP) Deadline Extended Second Call for Papers INTERNATIONAL CONFERENCE ON KNOWLEDGE BASED COMPUTER SYSTEMS National Centre for Software Technology Bombay, India December 16-18, 1996 THE DEADLINE FOR SUBMISSION OF PAPERS HAS NOW BEEN EXTENDED TO AUGUST 15, 1996 URL : http://konark.ncst.ernet.in/~kbcs/kbcs96.html ------------------------------ End of ML-LIST (Digest format) **************************************** From ZECCHINA@to.infn.it Mon Jul 1 20:25:36 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id UAA22624 for ; Mon, 1 Jul 1996 20:25:25 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id UAA10547 for ; Mon, 1 Jul 1996 20:25:23 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa25407; 1 Jul 96 15:21:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa25405; 1 Jul 96 15:07:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05571; 1 Jul 96 15:06:27 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa03021; 1 Jul 96 6:48:19 EDT Received: from [192.84.137.151] by EDRC.CMU.EDU id aa20766; 1 Jul 96 6:47:50 EDT Date: Mon, 1 Jul 1996 12:10:42 +0200 (MET-DST) From: "Riccardo Zecchina - tel.11-5647358, fax. 11-5647399" To: connectionists@cs.cmu.edu Message-Id: <960701121042.28201d6e@to.infn.it> Subject: Paper available on the Random K-Satisfiability Problem The following paper on algorithmic complexity is available by FTP. STATISTICAL MECHANICS OF THE RANDOM K-SATISFIABILITY PROBLEM by Remi Monasson and Riccardo Zecchina. ABSTRACT: The Random K-Satisfiability Problem, consisting in verifying the existence of an assignment of $N$ Boolean variables that satisfy a set of $M=\alpha N$ random logical clauses containing $K$ variables each, is studied using the replica symmetric framework of disordered systems. The detailed structure of the analytical solution is discussed for the different cases of interest $K=2$, $K\ge 3$ and $K\gg 1$. We present an iterative scheme allowing to obtain exact and systematically improved solutions for the replica symmetric functional order parameter. The caculation of the number of solutions, which allowed us [Phys. Rev. Lett. 76, 3881 (1996)] to predict a first order jump at the threshold where the Boolean expressions become unsatisfiable with probability one, is thoroughly displayed. In the case $K=2$, the (rigourously known) critical value ($=1$) of the number of clauses per Boolean variable is recovered while for $K\ge 3$ we show that the system exhibits a replica symmetry breaking transition. The annealed approximation is proven to be exact for large $K$. (30 pages + 8 figures) Retrieval information: FTP-host: ftp.polito.it FTP-pathname: /pub/people/zecchina/tarksat.gz URL: ftp://ftp.polito.it/pub/people/zecchina From matteo@nwu.edu Tue Jul 2 02:19:09 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA26931 for ; Tue, 2 Jul 1996 02:19:02 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id CAA13571 for ; Tue, 2 Jul 1996 02:19:00 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa25596; 1 Jul 96 17:53:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa25594; 1 Jul 96 17:43:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05671; 1 Jul 96 17:43:13 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa12293; 1 Jul 96 16:54:49 EDT Received: from hecky.acns.nwu.edu by RI.CMU.EDU id aa15890; 1 Jul 96 16:54:03 EDT Received: from [129.105.38.112] (maestrale.ls.nwu.edu) by hecky.acns.nwu.edu with SMTP (1.40.112.4/21.4) id AA013094383; Mon, 1 Jul 1996 15:53:03 -0500 X-Sender: mca578@hecky.acns.nwu.edu Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Mon, 1 Jul 1996 15:56:26 -0500 To: Connectionists@cs.cmu.edu From: Matteo Carandini Subject: Symposium on Orientation Selectivity Cc: somers@ai.mit.edu A Satellite Symposium to the 1996 Computation and Neural Systems CNS*96 Conference **** ORIENTATION SELECTIVITY IN V1. IS AN AGREEMENT POSSIBLE? ***** Wednesday, July 17, 7-10 pm Bldg. E 25, Room 401 Department of Brain and Cognitive Sciences, MIT Organized by Matteo Carandini (Northwestern) and David Somers (MIT) There is currently no agreement over whether the orientation selectivity of cells in the primary visual cortex results from the feed-forward arrangement of subcortical inputs or from intracortical feedback. This debate has gone on for about 30 years, and has recently been heated by the modeling work of Somers et al (J Neurosci 95), Douglas et al (Science 95), Suarez et al (J Neurosci 95) and Ben-Yishai et al (PNAS 95) and somewhat cooled by the experimental results of Ferster et al (Nature 96) and of Reid and Alonso (Nature 95). We encourage those with active research interests in this topic to attend, but also welcome those with more casual interest. We aim to stimulate discussion on the following issues: - The available evidence. The two sides in the debate sometimes cite the same references for opposite reasons. Let's discuss the evidence and decide what models are consistent with it. - The level of modeling. The existing models range from the very detailed (e.g Somers, Suarez), to the very simplified (e.g. Douglas, Ben-Yishai). What level of complexity should be achieved by a satisfactory model of orientation selectivity? - The ideal evidence. What would constitute unequivocal evidence against one of the two views? Is this evidence available or should new experiments be designed? *** Maximal participation by the audience will be encouraged. *** We have invited speakers with widely different opinions: - David Ferster (Northwestern) - Gary Holt (Caltech) - Xing Pei (Missouri) - Clay Reid (Harvard) - Dario Ringach (NYU) - Haim Sompolinsky (Hebrew U) A sizeable portion of the time will be spent in a free discussion. People with strong interest in the topic, like Bob Shapley (NYU), Mriganka Sur (MIT), Sacha Nelson (Brandeis) are expected to participate. --------------------------------------------------------------------------- Info on CNS*96 at http://www.bbb.caltech.edu/cns96/cns96.html From mccallum@cs.rochester.edu Tue Jul 2 02:19:12 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA26933 for ; Tue, 2 Jul 1996 02:19:04 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id CAA13573 for ; Tue, 2 Jul 1996 02:19:02 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa25757; 1 Jul 96 20:21:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa25754; 1 Jul 96 20:11:37 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05790; 1 Jul 96 20:10:35 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa14602; 1 Jul 96 19:36:49 EDT Received: from cayuga.cs.rochester.edu by RI.CMU.EDU id aa16654; 1 Jul 96 19:36:14 EDT Received: from slate.cs.rochester.edu (slate.cs.rochester.edu [192.5.53.101]) by cayuga.cs.rochester.edu (8.6.9/H) with ESMTP id TAA17516; Mon, 1 Jul 1996 19:30:25 -0400 Received: from vein.cs.rochester.edu (vein.cs.rochester.edu [192.5.53.112]) by slate.cs.rochester.edu (8.6.9/K) with SMTP id TAA06593; Mon, 1 Jul 1996 19:29:59 -0400 Message-Id: <199607012329.TAA06593@slate.cs.rochester.edu> To: connectionists@cs.cmu.edu, reinforce@cs.uwa.edu.au, intcon@phoenix.ee.unsw.edu.au, genetic-programming@cs.stanford.edu, learning@uran.informatik.uni-bonn.de, ml@ics.uci.edu Subject: Paper on RL, exploration, hidden state Date: Mon, 01 Jul 1996 19:29:55 -0400 From: Andrew McCallum The following paper on reinforcement learning, hidden state and exploration is available by FTP. Comments and suggestions are welcome. "Efficient Exploration in Reinforcement Learning with Hidden State" Andrew Kachites McCallum (submitted to NIPS) Abstract Undoubtedly, efficient exploration is crucial for the success of a learning agent. Previous approaches to directed exploration in reinforcement learning exclusively address exploration in Markovian domains, i.e. domains in which the state of the environment is fully observable. If the environment is only partially observable, they cease to work because exploration statistics are confounded between aliased world states. This paper presents Fringe Exploration, a technique for efficient exploration in partially observable domains. The key idea, (applicable to many exploration techniques), is to keep statistics in the space of possible short-term memories, instead of in the agent's current state space. Experimental results in a partially observable maze and in a difficult driving task with visual routines show dramatic performance improvements. Retrieval information: FTP-host: ftp.cs.rochester.edu FTP-pathname: /pub/papers/robotics/96.mccallum-nips.ps.gz URL: ftp://ftp.cs.rochester.edu/pub/papers/robotics/96.mccallum-nips.ps.gz From wahba@stat.wisc.edu Tue Jul 2 04:25:30 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id EAA27871 for ; Tue, 2 Jul 1996 04:25:24 -0500 Received: from hera.stat.wisc.edu (hera.stat.wisc.edu [128.105.5.29]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id EAA14247 for ; Tue, 2 Jul 1996 04:25:22 -0500 Date: Tue, 2 Jul 96 04:25:21 -0500 From: wahba@stat.wisc.edu (Grace Wahba) Message-Id: <9607020925.AA19638@hera.stat.wisc.edu> Received: by hera.stat.wisc.edu; Tue, 2 Jul 96 04:25:21 -0500 To: matteo@nwu.edu, ml@cs.wisc.edu Subject: Re: Symposium on Orientation Selectivity CC From ndxdpran@rrzn-user.uni-hannover.de Tue Jul 2 17:21:46 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA10445 for ; Tue, 2 Jul 1996 17:21:32 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id RAA22885 for ; Tue, 2 Jul 1996 17:21:30 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa27212; 2 Jul 96 15:55:16 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa27210; 2 Jul 96 15:37:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06867; 2 Jul 96 15:36:38 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa20757; 2 Jul 96 5:41:06 EDT Received: from mgate.uni-hannover.de by RI.CMU.EDU id aa18553; 2 Jul 96 5:37:48 EDT Received: from sun1.rrzn-user.uni-hannover.de (actually sun1) by mgate with SMTP (PP); Tue, 2 Jul 1996 11:37:01 +0200 Received: by sun1.rrzn-user.uni-hannover.de (SMI-8.6/SMI-SVR4) id LAA06163; Tue, 2 Jul 1996 11:36:48 +0200 From: ndxdpran@rrzn-user.uni-hannover.de Message-Id: <199607020936.LAA06163@sun1.rrzn-user.uni-hannover.de> Subject: ICOBIP'97 announcement To: connectionists@cs.cmu.edu Date: Tue, 2 Jul 1996 11:36:47 +0200 (MET DST) X-Mailer: ELM [version 2.4 PL25] Content-Type: text INTERNATIONAL CONFERENCE ON BIOLOGICAL INFORMATION PROCESSING ICOBIP'97 March 2-4, 1997, Hannover, Germany Topics: Basic Principles of Information Processing Cellular Systems Endocrine Systems Neuronal Systems Confirmed Speakers: - M. Berridge, Cambridge, UK - C. Schoefl, Hannover, Germany - S. Bezrukov, Bethesda, USA - T. Sejnowski, La Jolla, USA - T. Chay, Pittsburgh, USA - N. Spitzer, La Jolla, USA - J. Davidenko, Syracuse, USA - S. Stojilkovic, Bethesda, USA - J. Guckenheimer, Ithaca, USA - S. Strong, Princeton, USA - J. Keizer, Davis, USA - E. Szathmary, Budapest, Hungary - J. Reinitz, New York, USA Sponsored by: Deutsche Forschungsgemeinschaft, SIEMENS AG Organizing Committee: G. Brabant and K. Prank Medical School Hannover, Germany Registration forms may be obtained from: ICOBIP'97 - Organizing Committee Dept. of Clinical Endocrinology Medical School Hannover D-30623 Hannover Germany Phone: +49 511 532-6529 Fax: +49 511 532-3825 E-Mail: ndxdendo@rrzn-user.uni-hannover.de WWW: http://sun1.rrzn-user.uni-hannover.de/~ndxdeno/ICOBIP97.html From pierre@mbfys.kun.nl Tue Jul 2 21:09:11 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id VAA13190 for ; Tue, 2 Jul 1996 21:09:06 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id VAA25360 for ; Tue, 2 Jul 1996 21:09:04 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab27232; 2 Jul 96 16:04:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa27216; 2 Jul 96 15:41:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06889; 2 Jul 96 15:40:51 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa25142; 2 Jul 96 11:09:32 EDT Received: from septimius.mbfys.kun.nl by CS.CMU.EDU id aa09807; 2 Jul 96 11:05:03 EDT Received: from anthemius by septimius.mbfys.kun.nl via anthemius.mbfys.kun.nl [131.174.173.158] with SMTP id RAA19973 (8.6.10/2.4) for ; Tue, 2 Jul 1996 17:06:03 +0200 Sender: pierre@mbfys.kun.nl Message-ID: <31D93A92.15FB7483@mbfys.kun.nl> Date: Tue, 02 Jul 1996 17:04:50 +0200 From: "Pi\\\"erre van de Laar" Organization: KUN X-Mailer: Mozilla 2.01 (X11; I; SunOS 4.1.3_U1 sun4m) MIME-Version: 1.0 To: connectionists@cs.cmu.edu Subject: Re: sensitivity analysis and relevance Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Dear Connectionists, On my request for references to methods which perform sensitivity analysis and/or relevance determination of input fields, and especially methods which use neural networks, I received a large number of reactions with even a larger number of references. Due to the large size of the resulting list of references, I will not post it. People interested in this list of references can download it in bibtex, refer, or html format from ftp.mbfys.kun.nl in the directory snn/pub/pierre as file connectionists.bib , connectionists.refer ,or connectionists.html respectively. The URL for the HTML format is thus ftp://ftp.mbfys.kun.nl/snn/pub/pierre/connectionists.html Once again, I would like to thank all people who sent their references about these topics to me. Greetings, -- Pi\"erre van de Laar Department of Medical Physics and Biophysics, University of Nijmegen, The Netherlands http://www.mbfys.kun.nl/~pierre/ mailto:pierre@mbfys.kun.nl P.S. New references are, of course, still welcome. From psarroa@westminster.ac.uk Wed Jul 3 00:38:41 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id AAA14877 for ; Wed, 3 Jul 1996 00:38:35 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id AAA27308 for ; Wed, 3 Jul 1996 00:38:33 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa27232; 2 Jul 96 16:03:52 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa27214; 2 Jul 96 15:37:59 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06872; 2 Jul 96 15:37:01 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa21892; 2 Jul 96 6:45:57 EDT Received: from hare.wmin.ac.uk by CS.CMU.EDU id aa07768; 2 Jul 96 4:42:39 EDT Received: from jaguar.wmin.ac.uk by hare.wmin.ac.uk with SMTP (MMTA) with ESMTP; Tue, 2 Jul 1996 09:41:33 +0100 Received: (psarroa@localhost) by jaguar.wmin.ac.uk (8.6.12/8.6.12) id JAA27566 for Connectionists@cs.cmu.edu; Tue, 2 Jul 1996 09:41:30 +0100 From: Alexandra Psarrou Message-Id: <199607020841.JAA27566@jaguar.wmin.ac.uk> Subject: Research post in Face Recognition To: Connectionists@cs.cmu.edu Date: Tue, 2 Jul 1996 09:41:30 +0100 (BST) X-Mailer: ELM [version 2.4 PL23] Content-Length: 1612 MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" Research Post in Face Recognition CENTRE FOR ARTIFICIAL INTELLIGENCE RESEARCH Sir George Cayley Research Institute University of Westminster Applications are invited for the position of a Research Assistant in the Centre for AI Research of the University of Westminster to work in a one year research project in Machine Vision and Neural Networks. The successful candidate will undertake research in the area of Dynamic Face Recognition.The aim of this project is to exploit existing machine vision and neural network techniques for developing a framework for dynamic face recognition based on photometric representations. Applicants for this post should be educated to degree level within a relevant discipline (preferably computer science), and possess a working knowledge of C/C++/X-Windows on Unix platforms. Knowledge of image processing and neural network techniques will be an advantage. The post is available from July 1996 and the person appointed will be expected to start as soon as possible. Salary scales: Research A: 11,388 - 15,026 pounds sterling p.a., (including London allowance) - for more information about the project phone/email or send your CV to: Dr. Alexandra Psarrou School of Computer Science and Information Systems Engineering University of Westminster 115 New Cavendish Str London W1M 8JS Tel: (+44) - 171-911-5000 ext 3599 Fax: (+44) - 171-911-5089 Email: psarroa@westminster.ac.uk - for more information about the AI Research centre check our web page: http://www.scsise.wmin.ac.uk/AI/AI_Division.html From ndxdpran@rrzn-user.uni-hannover.de Wed Jul 3 15:34:06 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id PAA01153 for ; Wed, 3 Jul 1996 15:33:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id PAA07995 for ; Wed, 3 Jul 1996 15:33:57 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa28831; 3 Jul 96 14:12:47 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa28827; 3 Jul 96 13:52:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07908; 3 Jul 96 13:51:47 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ad00545; 3 Jul 96 6:50:21 EDT Received: from [130.75.2.3] by EDRC.CMU.EDU id aa02826; 3 Jul 96 5:51:38 EDT Received: from sun1.rrzn-user.uni-hannover.de (actually sun1) by mgate with SMTP (PP); Wed, 3 Jul 1996 11:50:08 +0200 Received: by sun1.rrzn-user.uni-hannover.de (SMI-8.6/SMI-SVR4) id LAA18829; Wed, 3 Jul 1996 11:49:55 +0200 From: ndxdpran@rrzn-user.uni-hannover.de Message-Id: <199607030949.LAA18829@sun1.rrzn-user.uni-hannover.de> Subject: ICOBIP'97 - correction of WWW home page To: connectionists@cs.cmu.edu Date: Wed, 3 Jul 1996 11:49:54 +0200 (MET DST) X-Mailer: ELM [version 2.4 PL25] Content-Type: text INTERNATIONAL CONFERENCE ON BIOLOGICAL INFORMATION PROCESSING ICOBIP'97 March 2-4, 1997, Hannover, Germany Topics: Basic Principles of Information Processing Cellular Systems Endocrine Systems Neuronal Systems Confirmed Speakers: - M. Berridge, Cambridge, UK - C. Schoefl, Hannover, Germany - S. Bezrukov, Bethesda, USA - T. Sejnowski, La Jolla, USA - T. Chay, Pittsburgh, USA - N. Spitzer, La Jolla, USA - J. Davidenko, Syracuse, USA - S. Stojilkovic, Bethesda, USA - J. Guckenheimer, Ithaca, USA - S. Strong, Princeton, USA - J. Keizer, Davis, USA - E. Szathmary, Budapest, Hungary - J. Reinitz, New York, USA Sponsored by: Deutsche Forschungsgemeinschaft, SIEMENS AG Organizing Committee: G. Brabant and K. Prank Medical School Hannover, Germany Registration forms may be obtained from: ICOBIP'97 - Organizing Committee Dept. of Clinical Endocrinology Medical School Hannover D-30623 Hannover Germany Phone: +49 511 532-6529 Fax: +49 511 532-3825 E-Mail: ndxdendo@rrzn-user.uni-hannover.de WWW: http://sun1.rrzn-user.uni-hannover.de/~ndxdendo/ICOBIP97.html From mrj@dcs.ed.ac.uk Wed Jul 3 15:34:18 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id PAA01156 for ; Wed, 3 Jul 1996 15:34:01 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id PAA07997 for ; Wed, 3 Jul 1996 15:33:58 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab28857; 3 Jul 96 14:25:50 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa28835; 3 Jul 96 13:54:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07920; 3 Jul 96 13:53:33 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ac02639; 3 Jul 96 10:44:41 EDT Received: from [129.215.160.105] by CS.CMU.EDU id aa19074; 3 Jul 96 10:43:38 EDT Received: from ox.dcs.ed.ac.uk by rainich.dcs.ed.ac.uk with SMTP (PP); Wed, 3 Jul 1996 15:43:11 +0100 Date: Wed, 3 Jul 1996 15:43:08 +0100 Message-Id: <17667.9607031443@ox.dcs.ed.ac.uk> To: connectionists@cs.cmu.edu Subject: ICMS Workshop on the Vapnik-Chervonenkis Dimension, Edinburgh From: Mark Jerrum [For distribution on the connectionist mailing list: thanks!] ************************************************************** *** *** *** ICMS WORKSHOP on the VAPNIK-CHERVONENKIS DIMENSION *** *** Edinburgh, 9th--13th September 1996 *** *** *** *** An interdisciplinary meeting of interest to *** *** probabilists, statisticians, theoretical computer *** *** scientists, and the machine learning community *** *** *** ************************************************************** The International Centre for Mathematical Sciences (ICMS) at Edinburgh will hold a Workshop on the Vapnik-Chervonenkis Dimension(*) in the week 9th--13th September 1996. The workshop will take place at the ICMS's headquarters at 14 India Street, Edinburgh, the birthplace of James Clerk Maxwell, which has recently been adapted to support meetings with about 50 participants. We (the organisers or the workshop) envisage a multidisciplinary meeting covering the topic in all its aspects: probability and statistics, computational learning theory, geometry, and applications in computer science. The following invited speakers have agreed to participate: Shai Ben-David, Technion, Haifa, Israel; David Haussler, University of California at Santa Cruz, USA; Jiri Matousek, Charles University, Prag, Czech Republic; V. N. Vapnik, AT&T Bell Laboratories, Holmdel, NJ, USA. A registration form is available from the workshop's WWW page at http://www.dcs.ed.ac.uk/~mrj/VCWorkshop/ (also accessible from the ICMS home page). Alternatively, intending participants may contact the ICMS by post or e-mail: Margaret Cook ICMS 14 India Street Edinburgh EH3 6EZ Scotland Phone: +44 (0)131-220-1777 Fax: +44 (0)131-220-1053 E-mail: icms@maths.ed.ac.uk Those interested in participating should return the registration form as soon as possible, as the total number of places is limited by the size of the venue. There will be ample scope for contributed talks. Mark Jerrum, Angus MacIntyre, and John Shawe-Taylor (Workshop organisers) (*) The Vapnik-Chervonenkis (VC) dimension is a combinatorial parameter of a set system (equivalently, of a class of predicates) which, informally, can be said to characterise the expressibility of the class. This parameter is of great significance in a wide range of applications: in statistics, theoretical computer science, and machine learning, for example. In statistics, one may identify ``set'' with ``event,'' in which case finite VC dimension entails a _uniform_ analogue of the strong law of large numbers for the class of events in question. (This is the situation described by the phrase ``uniform convergence of empirical measure.'') In learning theory (the mathematical theory of inductive inference), one may identify ``set'' with ``concept,'' in which case the VC dimension of the concept class gives quite tight bounds on the sample size that is necessary and sufficient for a learner to form an accurate hypothesis from classified examples. From c.k.i.williams@aston.ac.uk Wed Jul 3 23:11:52 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id XAA04618 for ; Wed, 3 Jul 1996 23:11:46 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id XAA12148 for ; Wed, 3 Jul 1996 23:11:44 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa28857; 3 Jul 96 14:24:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa28833; 3 Jul 96 13:53:12 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07914; 3 Jul 96 13:52:31 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa01973; 3 Jul 96 9:56:34 EDT Received: from email.aston.ac.uk by EDRC.CMU.EDU id aa03590; 3 Jul 96 9:56:03 EDT Received: from sun.aston.ac.uk (actually host markov.aston.ac.uk) by email.aston.ac.uk with SMTP (PP); Wed, 3 Jul 1996 14:57:59 +0100 Message-Id: <10110.199607031353@sun.aston.ac.uk> To: Connectionists@cs.cmu.edu, allstat@mailbase.ac.uk From: Chris Williams Subject: Post-doc research position at Aston University, England Date: Wed, 03 Jul 1996 15:53:50 +0200 Sender: willicki@helios.aston.ac.uk Postdoctoral Research Fellowship at Aston University, England Combining Spatially-Distributed Predictions from Neural Networks The Neural Computing Research Group at Aston is looking for a highly motivated individual for a 2 year postdoctoral research position in the area of "Combining Spatially-Distributed Predictions from Neural Networks", working with Dr. Chris Williams and Dr. Ian Nabney. The aim of this project is to develop methods for the fusion of spatially-distributed predictions from neural networks with prior knowledge about possible spatial patterns. This post is funded by a grant from the Engineering and Physical Sciences Research Council (UK), in collaboration with British Aerospace and the Meteorological Office. Potential candidates should have strong mathematical and computational skills, with a background one or more of neural networks, Bayesian belief networks and statistical Markov chain Monte Carlo computation. Neural networks have been used very successfully in a wide variety of domains for performing classification or regression tasks. A characteristic of most currently successful applications is that the input patterns are either independent (as in static pattern classification) or related over time, rather than being spatially distributed. To extend the use of neural networks to spatially distributed tasks, such as the prediction of a wind vector-field from remote-sensing data, typically it is necessary to combine local bottom-up predictions (wind vector predictions on a pixel-by-pixel basis) with global prior knowledge (typical wind-field configurations, including weather fronts). This combination can be achieved by using Bayes' theorem to obtain the posterior distribution for the features of interest (the wind-field). The project will apply this framework in the areas of remote sensing, the segmentation of images, and object recognition. Closing date: 29 July, 1996. Informal enquiries can be made by email to Chris Williams (C.K.I.Williams@aston.ac.uk) or to Ian Nabney (I.T.Nabney@aston.ac.uk). The target start date is October 1996, although this may be somewhat flexible, More information on the Neural Computing Research Group and the postdoc position is available from http://www.ncrg.aston.ac.uk/ Salaries will be up to point 6 on the RA 1A scale, currently 15,986 UK pounds. These salary scales are subject to annual increments. If you wish to be considered for this position, please send a full CV and publications list, together with the names of 3 referees, to: Dr. Chris Williams Neural Computing Research Group Department of Computer Science and Applied Mathematics Aston University Birmingham B4 7ET, U.K. Tel: +44 121 333 4631 Fax: +44 121 333 4586 e-mail: C.K.I.Williams@aston.ac.uk (email submission of postscript files is welcome) From chandler@kryton.ntu.ac.uk Thu Jul 4 06:22:09 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id GAA06893 for ; Thu, 4 Jul 1996 06:22:04 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id GAA14352 for ; Thu, 4 Jul 1996 06:22:02 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00379; 4 Jul 96 5:26:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00377; 4 Jul 96 5:14:46 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08761; 4 Jul 96 5:14:36 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa15630; 4 Jul 96 5:02:05 EDT Received: from www.ntu.ac.uk by CS.CMU.EDU id aa26487; 4 Jul 96 5:01:28 EDT Received: from kryton.ntu.ac.uk by pixie.ntu.ac.uk with SMTP (PP); Thu, 4 Jul 1996 10:01:31 +0100 Received: by kryton.ntu.ac.uk (5.0/SMI-SVR4) id AA01426; Thu, 4 Jul 1996 10:03:27 +0000 Date: Thu, 4 Jul 1996 10:03:27 +0000 From: chandler Message-Id: <9607040903.AA01426@kryton.ntu.ac.uk> To: connectionists@cs.cmu.edu Subject: PhD Research Positions available, Nottingham England X-Sun-Charset: US-ASCII content-length: 3697 VACANCIES Research (2 Bursary Students) Object Recognition for Assembly Human Centred Assembly Introduction The Manufacturing Automation Research Group (MARG) has been working on the development of Artificial Intelligence techniques for the recognition of 3-D objects. The aim of this work is to develop a system for the recognition of solid objects independent of their position and orientation within the work domain. This is to aid in the manipulation of objects within a robotic cell, particularly for the processes of assembly and other manipulative tasks . In the formation of this work, a novel method using ANN with parallels to the processing within the primate visual system, has been used. The Programme Object Recognition for Assembly The aim of this project is to improve the fundamental understanding of object recognition for use in assembly process. The major area of the research will be the implementation of novel techniques of object recognition, and provide position and rotation parameters to enable assembly tasks to be executed. The ANN techniques already developed in-house will be extended and integrated with the robot, providing invariant object recognition capability to the system. Additionally the geometric descriptors will be assessed for their validity/accuracy. Task level robotic operations can then use these descriptors as a base for further actions. Human Centred Assembly Whilst the sections of the research programme described above will provide both novel and effective robotic assembly, this section of the work seeks to draw the maximum knowledge from existing manual methods. It therefore provides an effective link, drawing knowledge from the manual operation and contributing to the learning of a manipulative skill by a machine. The work will analyse human centred assembly strategies and contrast them with automation techniques. Methods which are applicable to sensory challenged human assembly will be interpreted and applied to the sensor equipped robot. Applications invited from Graduates (Engineering, Science) with good classifications Bursary 6,000 UKP / annum for 3 years Applicants will be expected to register for a PhD programme. References 1) Keat J, Balendran V, Sivayoganathan K. 1995. Invariant Object Recognition with a Neurobiological Slant, Proceeding of the Fourth IEE International Conference on Artificial Neural Networks, Cambridge. 2) Keat J, Balendran V, Sivayoganathan K, Sackfield A. "IvOR: A Neurobiologically slanted approach to PSRI Object recognition", 5th Irish Neural Network Conference - INNC95, September 11-13, 1995, pp. 30-37, Maynooth, Ireland. 3) Howarth M, Sivayoganathan K, Thomas P, Gentle C.R., "Robotic task level programming using neural networks", 4th Int. Conf.on Artificial Neural Networks, 26-28 June 1995. pp 262-267. Churchill College, Cambridge. 4) Balendran V, Sivayoganathan K, Al-Dabass D. 1989. Detection of flaws on slowly varying surfaces, Proceedings of the Fifth National Conference on Production Research, London, Kogan Press, pp82-85. 5) Keat J, Balendran V, Sivayoganathan K, Sackfield A. 1994. 3-D data collection for object recognition, Advances in Manufacturing Technology VIII, Proceedings of the Tenth National Conference on Manufacturing Research, Loughborough, pp648-652. Contact: Dr. K. Sivayoganathan man3sivayk@ntu.ac.uk tel: +44(0)115 941 8418 ex 4112. Dr. S. Kennedy man3kennesj@ntu.ac.uk tel: +44(0)115 941 8418 ex 4106. Mr. M. Howarth m.howarth@marg.ntu.ac.uk tel: +44(0)115 941 8418 ex 4110. Manufacturing Automation Research Group Department of Manufacturing Engineering, Burton Street, Nottingham, NG1 4BU. fax: +44(0)115 941 4024 From kevin.swingler@psych.stir.ac.uk Thu Jul 4 16:41:40 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA14291 for ; Thu, 4 Jul 1996 16:41:34 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id QAA18115 for ; Thu, 4 Jul 1996 16:41:32 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa01089; 4 Jul 96 16:04:21 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa01073; 4 Jul 96 15:51:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09120; 4 Jul 96 15:50:25 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa17368; 4 Jul 96 7:43:31 EDT Received: from [139.153.13.14] by EDRC.CMU.EDU id aa08954; 4 Jul 96 7:43:04 EDT Received: from nevis.stir.ac.uk by bannock with SMTP (PP) id <19520-0@bannock>; Thu, 4 Jul 1996 12:42:55 +0100 Received: by nevis.stir.ac.uk (1.38.193.4/16.2) id AA21529; Thu, 4 Jul 1996 12:42:54 +0100 From: Kevin Swingler Message-Id: <9607041142.AA21529@nevis.stir.ac.uk> Subject: New Book Applying Neural Networks To: connectionists@cs.cmu.edu Date: Thu, 4 Jul 96 12:42:54 BST Mailer: Elm [revision: 70.85] *********************************************************************** NEW BOOK ANNOUNCEMENT Applying Neural Networks A Practical Guide Kevin Swingler Academic Press. ISBN: 0126791708 *********************************************************************** Description This book takes the most common neural network architecture--the multi-layer perceptron--and leads the reader through every step the development of a trained network. Chapters cover data collection, quantity, quality, validation, preparation and encoding; network arcitecture, size and training; error analysis ; network validation, confidence limits, sensitivity measures and rule derivation. The book also covers novelty detection and time series analysis. The book presents a set of procedures designed to ensure succsessful network development and is concluded with a set of demonstration chapters on the application of neural networks to signal processing, financial analysis and process control. Each chapter is divided into three sections: A general discussion without equations, a how-to-do-it section where equations and algorithms are layed out, and a set of worked examples. The book also comes with a disk of C and C++ programs which implement the techniques discussed. Ordering Applying Neural Networks may be ordered directly from Academic Press or from your usual retail outlets.