From crites@hope.cs.umass.edu Mon Oct 28 12:42:58 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 MAA25241 for ; Mon, 28 Oct 1996 12:42:50 -0600 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 MAA08060 for ; Mon, 28 Oct 1996 12:42:48 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03575; 28 Oct 96 12:28:29 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03573; 28 Oct 96 12:02:31 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa20909; 28 Oct 96 12:02:02 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa24625; 28 Oct 96 1:06:26 EST Received: from hope.cs.umass.edu by EDRC.CMU.EDU id aa24741; 28 Oct 96 1:06:22 EST Received: (from crites@localhost) by hope.cs.umass.edu (8.7.6/8.6.9) id BAA08370; Mon, 28 Oct 1996 01:06:19 -0500 (EST) From: Bob Crites Message-Id: <199610280606.BAA08370@hope.cs.umass.edu> Subject: PhD Thesis Available To: connectionists@cs.cmu.edu Date: Mon, 28 Oct 1996 01:06:18 -0500 (EST) Cc: Bob Crites X-Mailer: ELM [version 2.4 PL25] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit My Phd thesis is now available for download: LARGE-SCALE DYNAMIC OPTIMIZATION USING TEAMS OF REINFORCEMENT LEARNING AGENTS Robert Harry Crites ftp://ftp.cs.umass.edu/pub/anw/pub/crites/root.ps.Z (202517 bytes) or from my homepage at: http://www-anw.cs.umass.edu/People/crites/crites.html Abstract: Recent algorithmic and theoretical advances in reinforcement learning (RL) are attracting widespread interest. RL algorithms have appeared that approximate dynamic programming (DP) on an incremental basis. Unlike traditional DP algorithms, these algorithms do not require knowledge of the state transition probabilities or reward structure of a system. This allows them to be trained using real or simulated experiences, focusing their computations on the areas of state space that are actually visited during control, making them computationally tractable on very large problems. RL algorithms can be used as components of multi-agent algorithms. If each member of a team of agents employs one of these algorithms, a new collective learning algorithm emerges for the team as a whole. In this dissertation we demonstrate that such collective RL algorithms can be powerful heuristic methods for addressing large-scale control problems. Elevator group control serves as our primary testbed. The elevator domain poses a combination of challenges not seen in most RL research to date. Elevator systems operate in continuous state spaces and in continuous time as discrete event dynamic systems. Their states are not fully observable and they are non-stationary due to changing passenger arrival rates. As a way of streamlining the search through policy space, we use a team of RL agents, each of which is responsible for controlling one elevator car. The team receives a global reinforcement signal which appears noisy to each agent due to the effects of the actions of the other agents, the random nature of the arrivals and the incomplete observation of the state. In spite of these complications, we show results that in simulation surpass the best of the heuristic elevator control algorithms of which we are aware. These results demonstrate the power of RL on a very large scale stochastic dynamic optimization problem of practical utility. From lenherr@mildura.cs.umass.edu Mon Oct 28 20:07:38 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 UAA02978 for ; Mon, 28 Oct 1996 20:07:33 -0600 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 UAA15852 for ; Mon, 28 Oct 1996 20:07:32 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03584; 28 Oct 96 12:38:00 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03577; 28 Oct 96 12:08:07 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa20926; 28 Oct 96 12:07:18 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa11454; 27 Oct 96 1:09:45 EST Received: from mildura.cs.umass.edu by CS.CMU.EDU id aa26858; 27 Oct 96 1:09:04 EST Received: (from lenherr@localhost) by mildura.cs.umass.edu (8.7.6/8.7.3) id BAA06192 for neuro; Sun, 27 Oct 1996 01:01:15 -0500 Date: Sun, 27 Oct 1996 01:01:15 -0500 From: Fred Lenherr Message-Id: <199610270601.BAA06192@mildura.cs.umass.edu> To: neuro@mildura.cs.umass.edu Subject: Neuroscience Web Search Hello, I have created a new Web Search Engine devoted entirely to neuroscience. Unlike the large search sites, everything here is relevant by pre-selection. The URL is: http://www.acsiom.org/nsr/neuro.html This is a full-text database and contains more than 55,000 web pages. If you are interested, please take a look at it, and consider placing a link to it on one of your own web pages. Thanks very much, Fred K. Lenherr From schapire@research.att.com Tue Oct 29 00:48:55 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 AAA04445 for ; Tue, 29 Oct 1996 00:48:48 -0600 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 AAA19109 for ; Tue, 29 Oct 1996 00:48:46 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03748; 28 Oct 96 14:52:42 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03746; 28 Oct 96 14:42:38 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa21041; 28 Oct 96 14:42:01 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa02164; 28 Oct 96 12:12:23 EST Received: from ns.research.att.com by CS.CMU.EDU id aa05965; 28 Oct 96 12:12:10 EST Received: from research.att.com by ns; Mon Oct 28 12:11:01 EST 1996 Received: from amontillado.research.att.com by research; Mon Oct 28 12:08:28 EST 1996 Received: from arran.research.att.com (arran.research.att.com [135.205.42.12]) by amontillado.research.att.com (8.7.5/8.7) with ESMTP id MAA29131; Mon, 28 Oct 1996 12:08:00 -0500 (EST) Received: (from schapire@localhost) by arran.research.att.com (8.7.5/8.7) id MAA06414; Mon, 28 Oct 1996 12:07:59 -0500 (EST) Date: Mon, 28 Oct 1996 12:07:59 -0500 (EST) Message-Id: <199610281707.MAA06414@arran.research.att.com> From: Robert Schapire To: ai-stats@watstat.uwaterloo.ca, bayes-news@stat.cmu.edu, cogpsy@neuro.psy.soton.ac.uk, colt@cs.uiuc.edu, connectionists@cs.cmu.edu, dietmar@cognition.iig.uni-freiburg.de, dmanet@math.utwente.nl, genetic-programming@cs.stanford.edu, hybrid-list@cs.ua.edu, ilpnet@ijs.si, kdd@gte.com, ml@ics.uci.edu, mlnet@swi.psy.uva.nl, news-announce-conferences@uunet.uu.net, reinforce@cs.uwa.edu.au, sigart@vaxa.isi.edu, theory-a@vm1.nodak.edu, uai@maillist.cs.orst.edu Subject: Call for papers: COLT '97 =========================================================================== -- Call for Papers -- COLT '97 Tenth Annual Conference on Computational Learning Theory Vanderbilt University, Nashville, Tennessee July 6--9, 1997 =========================================================================== The Tenth Annual Conference on Computational Learning Theory (COLT'97) will be held at Vanderbilt University in Nashville, Tennessee from Sunday, July 6 through Wednesday, July 9, 1997. COLT'97 is sponsored by Vanderbilt University, with additional support from AT&T Labs, and in cooperation with ACM SIGACT and SIGART. The conference will be co-located with the Fourteenth International Conference on Machine Learning (ICML'97) which will be held Tuesday, July 8 through Saturday, July 12. We anticipate a lively program including oral presentations, posters, a number of invited speakers and a half day of tutorials (jointly organized with ICML). We invite papers in all areas that relate directly to the analysis of learning algorithms and the theory of machine learning. Some of the issues and topics that have been addressed in the past include: * design and analysis of learning algorithms; * sample and computational complexity of learning specific model classes; * frameworks modeling the interaction between the learner, teacher and the environment (such as learning with queries, learning control policies and inductive inference); * learning using complex models (such as neural networks and decision trees); * learning with minimal prior assumptions (such as mistake-bound models, universal prediction, and agnostic learning). We strongly encourage submissions from all disciplines engaged in research on these and related questions. Examples of such fields include computer science, statistics, information theory, pattern recognition, statistical physics, inductive logic programming, information retrieval and reinforcement learning. We also encourage the submission of papers describing experimental results that are supported by theoretical analysis. ABSTRACT SUBMISSION: Authors are encouraged to submit their abstracts electronically. Instructions for how to submit papers electronically can be obtained after December 1 by sending email to colt97@research.att.com with subject "help", or from our web page. Alternatively, authors may submit fourteen copies (preferably two-sided) of an extended abstract to: Robert Schapire -- COLT'97 AT&T Labs 600 Mountain Avenue, Room 2A-424 Murray Hill, NJ 07974 USA Telephone (for overnight mail): (908) 582-4533 Abstracts (whether hard-copy or electronic) must be RECEIVED by 11:59pm EST on FRIDAY, JANUARY 17, 1997. This deadline is FIRM. (We also will accept abstracts sent via air mail and postmarked by January 6, or sent via overnight carrier by January 16.) Authors will be notified of acceptance or rejection on or before March 24, 1997. Final camera-ready papers will be due by April 18. Papers that have appeared in journals or other conferences, or that are being submitted to other conferences (including ICML), are NOT appropriate for submission to COLT. ABSTRACT FORMAT: The extended abstract should consist of a cover page with title, authors' names, postal and email addresses, and a 200-word summary. The body of the abstract should be no longer than 10 pages with at most 35 lines per page, at most 6.5 inches of text per line, and in 12-point font. If the abstract exceeds 10 pages, only the first 10 pages may be examined. The extended abstract should include a clear definition of the theoretical model used and a clear description of the results, as well as a discussion of their significance, including comparison to other work. Proofs or proof sketches should be included. PROGRAM FORMAT: All accepted papers will be presented orally, although some or all papers may also be included in a poster session. At the discretion of the program committee, the program may consist of both long and short talks, corresponding to longer and shorter papers in the proceedings. By default, all papers will be considered for both categories. Authors who DO NOT want their papers considered for the short category should indicate that fact in a cover letter. PROGRAM CHAIRS: Yoav Freund and Robert Schapire (AT&T Labs). PROGRAM COMMITTEE: Andrew Barron (Yale University), John Case (University of Delaware), Sally Goldman (Washington University), David Helmbold (University of California, Santa Cruz), Rob Holte (University of Ottawa), Eyal Kushilevitz (Technion), Ga`bor Lugosi (Pompeu Fabra University, Barcelona), Arun Sharma (University of New South Wales), John Shawe-Taylor (University of London), Satinder Singh (University of Colorado, Boulder), Haim Sompolinsky (Hebrew University), Volodya Vovk (Royal Holloway, University of London). CONFERENCE AND LOCAL ARRANGEMENTS CHAIR: Vijay Raghavan (Vanderbilt University). STUDENT TRAVEL: We anticipate some funds will be available to partially support travel by student authors. Details will be distributed as they become available. TUTORIALS: The program will include a half day of tutorials, jointly organized by COLT and ICML, and intended as introductions to topics in the theory and practice of machine learning. For further information, or to submit a proposal for a tutorial, contact Sally Goldman, the tutorials chair, at sg@cs.wustl.edu or visit our web page. FOR MORE INFORMATION: Visit the ICML/COLT'97 web page at http://cswww.vuse.vanderbilt.edu/~mlccolt/, or send email to colt97@research.att.com. This call for papers is available in html and other formats from http://www.research.att.com/~yoav/colt97/cfp.html From john@dcs.rhbnc.ac.uk Tue Oct 29 00:48:56 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 AAA04447 for ; Tue, 29 Oct 1996 00:48:49 -0600 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 AAA19111 for ; Tue, 29 Oct 1996 00:48:47 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03828; 28 Oct 96 16:18:58 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03826; 28 Oct 96 16:07:53 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa21102; 28 Oct 96 16:07:49 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa07306; 28 Oct 96 15:41:15 EST Received: from [134.219.44.52] by CS.CMU.EDU id aa08385; 28 Oct 96 15:40:46 EST Received: from localhost (localhost [127.0.0.1]) by platon.cs.rhbnc.ac.uk (8.6.9/8.6.9) with SMTP id UAA12033 ; Mon, 28 Oct 1996 20:40:39 GMT From: John Shawe-Taylor Message-Id: <199610282040.UAA12033@platon.cs.rhbnc.ac.uk> X-Authentication-Warning: platon.cs.rhbnc.ac.uk: Host localhost didn't use HELO protocol To: colt@cs.uiuc.edu, Connectionists@cs.cmu.edu, enns-list@dcs.kcl.ac.uk, neur-sci@dl.ac.uk, comp-neuro@smaug.bbb.caltech.edu, neuron-request@cattell.psych.upenn.edu Subject: Special Issue on VC Dimension Date: Mon, 28 Oct 96 20:40:39 +0000 X-Mts: smtp DISCRETE APPLIED MATHEMATICS announcing a Special Issue on Vapnik-Chervonenkis Dimension Manuscripts are solicited for a special issue of DISCRETE APPLIED MATHEMATICS on the topic of the Vapnik-Chervonenkis Dimension. The special issue arose out of an ICMS Workshop on the VC Dimension though submission is not restricted to those who attended the workshop. For more information on the Vapnik-Chervonenkis dimension and the aims of the workshop and hence also the Special Issue, please consult the `scientific aims' available through the homepage: http://www.dcs.ed.ac.uk/~mrj/VCWorkshop/ The following is a (nonexhaustive) list of possible topics of interest for the SPECIAL ISSUE: - Combinatorics of the VC Dimension - Applications of the VC Dimension in Statistics - Applications of the VC Dimension in Learning Theory - Applications of the VC Dimension in Computational Geometry - Applications of the VC Dimension in Complexity Theory Four (4) copies of complete manuscripts should be sent to the Coordinating Editor indicated below by December 31, 1996. Email submission of postscript files (preferably compressed and uuencoded) is acceptable. Manuscripts must be prepared according to the normal submission requirements of Discrete Applied Mathematics, as described inside the back cover of each issue of the journal. All manuscripts will be subject to the regular refereeing process of the journal. Papers should include an abstract. The Guest Editors of the Special Issue are: Coordinating Editor: J.S. Shawe-Taylor Department of Computer Science Royal Holloway, University of London Egham, Surrey TW20 0EX UK Email: jst@dcs.rhbnc.ac.uk A. Macintyre Mathematical Institute Oxford University Email: ajm@maths.ox.ac.uk M. Jerrum Department of Computer Science University of Edinburgh Email: mrj@dcs.edinburgh.ac.uk ------- End of Forwarded Message From carl@cs.toronto.edu Tue Oct 29 18:05:15 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 SAA03517 for ; Tue, 29 Oct 1996 18:05:08 -0600 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 SAA03008 for ; Tue, 29 Oct 1996 18:05:05 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06105; 29 Oct 96 17:13:50 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06049; 29 Oct 96 16:42:25 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22182; 29 Oct 96 16:41:55 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa03061; 29 Oct 96 15:52:21 EST Received: from yonge.cs.toronto.edu by RI.CMU.EDU id aa27110; 29 Oct 96 15:51:34 EST Received: from neuron.ai.toronto.edu ([128.100.3.14]) by yonge.cs.toronto.edu with SMTP id <86557>; Tue, 29 Oct 1996 15:50:21 -0500 Received: by neuron.ai.toronto.edu id <987>; Tue, 29 Oct 1996 15:50:11 -0500 From: Carl Edward Rasmussen To: connectionists@cs.cmu.edu Subject: PhD thesis available Message-Id: <96Oct29.155011edt.987@neuron.ai.toronto.edu> Date: Tue, 29 Oct 1996 15:50:10 -0500 My PhD thesis is now available on the net. It is entitled EVALUATION OF GAUSSIAN PROCESSES AND OTHER METHODS FOR NON-LINEAR REGRESSION The thesis is 138 pages long, occupies 460Kb in compressed postscript and is formatted for double-sided printing. You can obtain a copy via the web at http://www.cs.toronto.edu/~carl/pub.html or via anonymous ftp to ftp.cs.toronto.edu where the file "thesis.ps.gz" is placed in the directory "pub/carl". ABSTRACT: This thesis develops two Bayesian learning methods relying on Gaussian processes and a rigorous statistical approach for evaluating such methods. In these experimental designs the sources of uncertainty in the estimated generalisation performances due to both variation in training and test sets are accounted for. The framework allows for estimation of generalisation performance as well as statistical tests of significance for pairwise comparisons. Two experimental designs are recommended and supported by the DELVE software environment. Two new non-parametric Bayesian learning methods relying on Gaussian process priors over functions are developed. These priors are controlled by hyperparameters which set the characteristic length scale for each input dimension. In the simplest method, these parameters are fit from the data using optimization. In the second, fully Bayesian method, a Markov chain Monte Carlo technique is used to integrate over the hyperparameters. One advantage of these Gaussian process methods is that the priors and hyperparameters of the trained models are easy to interpret. The Gaussian process methods are benchmarked against several other methods, on regression tasks using both real data and data generated from realistic simulations. The experiments show that small datasets are unsuitable for benchmarking purposes because the uncertainties in performance measurements are large. A second set of experiments provide strong evidence that the bagging procedure is advantageous for the Multivariate Adaptive Regression Splines (MARS) method. The simulated datasets have controlled characteristics which make them useful for understanding the relationship between properties of the dataset and the performance of different methods. The dependency of the performance on available computation time is also investigated. It is shown that a Bayesian approach to learning in multi-layer perceptron neural networks achieves better performance than the commonly used early stopping procedure, even for reasonably short amounts of computation time. The Gaussian process methods are shown to consistently outperform the more conventional methods. -- \ Carl Edward Rasmussen Email: carl@cs.toronto.edu o/\_ Dept of Computer Science Phone: +1 (416) 978 7391 <|__,\ University of Toronto, Home : +1 (416) 531 5685 "> | Toronto, ONTARIO, FAX : +1 (416) 978 1455 ` | Canada, M5S 1A4 web : http://www.cs.toronto.edu/~carl From marshall@cs.unc.edu Tue Oct 29 18:05:29 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 SAA03519 for ; Tue, 29 Oct 1996 18:05:09 -0600 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 SAA03010 for ; Tue, 29 Oct 1996 18:05:07 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab06105; 29 Oct 96 17:14:54 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab06049; 29 Oct 96 16:42:27 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22189; 29 Oct 96 16:42:18 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa29263; 29 Oct 96 12:34:49 EST Received: from mcenroe.cs.unc.edu by EDRC.CMU.EDU id aa03861; 29 Oct 96 12:34:30 EST Received: from marshall.cs.unc.edu by mcenroe.cs.unc.edu (8.6.10/UNC_06_21_94) id MAA17594; Tue, 29 Oct 1996 12:31:45 -0500 From: Jonathan Marshall Received: by marshall.cs.unc.edu (8.6.10/UNC_06_21_94) id NAA17815; Tue, 29 Oct 1996 13:31:39 -0400 Date: Tue, 29 Oct 1996 13:31:39 -0400 Message-Id: <199610291731.NAA17815@marshall.cs.unc.edu> To: cogneuro@ptolemy-ethernet.arc.nasa.gov, comp-neuro@smaug.bbb.caltech.edu, connectionists@cs.cmu.edu, cvnet@skivs.ski.org, cybsys-l@bingvmb.cc.binghamton.edu, inns-l%umdd.bitnet@pucc.princeton.edu, issnnet-mlist@CNS.BU.EDU, ml@ics.uci.edu, mpsych-l@brownvm.brown.edu, neuron@cattell.psych.upenn.edu, nycvisionpeople@robocop.nyu.edu, psyc@pucc.princeton.edu, vision-list@teleosresearch.com, visres-cortical@mailbase.ac.uk Subject: Short-term postdoc opening: Neural modeling of visual perception ---------------------------------------------------------------------------- Short-Term Position Opening: POSTDOCTORAL RESEARCH ASSOCIATE IN NEURAL MODELING OF VISUAL PERCEPTION at the University of North Carolina at Chapel Hill A short-term postdoctoral position is available in neural modeling of visual perception, in Dr. Jonathan Marshall's research group at UNC-Chapel Hill. The group's research focuses on intermediate-level visual motion perception, surface appearance perception, object perception, binding and grouping, and depth perception. The opening is the 2nd postdoctoral position in a research group that includes one faculty member, one postdoc, and four PhD students. The postdoc will develop and implement computational simulations of neural models of visual mechanisms involved in perception of surface brightness and transparency, depth, motion, and other aspects of visual and neural processing. The postdoc will also work on developing relative-motion algorithms for image processing tasks in object detection, image stabilization, scene segmentation, and invariant object representation. The postdoc may also have opportunities to develop and run visual psychophysics experiments on motion perception and stereopsis. The project includes work on adaptation and self-organization processes that may guide the development and maintenance of such neural mechanisms in human and animal brains. The postdoc will collaborate with other members of the research group. The position requires very good programming skills and (ideally) some image processing and/or neural simulation experience. Experience with visual psychophysics or visual neurophysiology would be a plus. The position is available immediately and is funded for 6 or more months. Because the position is short-term, it might be ideal for a new PhD who needs interim funding before starting another position in the Summer or Fall. Salary is competitive. Please send CV, a letter describing research interests and background, relevant publications, and references to Prof. Jonathan A. Marshall, Department of Computer Science, CB 3175, Sitterson Hall, University of North Carolina, Chapel Hill, NC 27599-3175, USA. Phone 919-962-1887, fax 919-962-1799, marshall@cs.unc.edu, http://www.cs.unc.edu/~marshall. Posted 25 October 1996 ---------------------------------------------------------------------------- From marshall@cs.unc.edu Tue Oct 29 20:52:19 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 UAA05228 for ; Tue, 29 Oct 1996 20:52:08 -0600 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 UAA05468 for ; Tue, 29 Oct 1996 20:52:07 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06047; 29 Oct 96 17:04:04 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06045; 29 Oct 96 16:41:35 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22173; 29 Oct 96 16:40:30 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa27540; 29 Oct 96 11:11:51 EST Received: from mcenroe.cs.unc.edu by CS.CMU.EDU id aa15125; 29 Oct 96 11:11:30 EST Received: from marshall.cs.unc.edu by mcenroe.cs.unc.edu (8.6.10/UNC_06_21_94) id LAA13248; Tue, 29 Oct 1996 11:04:13 -0500 From: Jonathan Marshall Received: by marshall.cs.unc.edu (8.6.10/UNC_06_21_94) id MAA17472; Tue, 29 Oct 1996 12:03:55 -0400 Date: Tue, 29 Oct 1996 12:03:55 -0400 Message-Id: <199610291603.MAA17472@marshall.cs.unc.edu> To: INNS-L%UMDD.BitNet@pucc.PRINCETON.EDU, binoc@research.canon.oz.au, cogneuro@ptolemy-ethernet.arc.nasa.gov, cogni-info@univ-lyon1.fr, cogpsy@phil.ruu.nl, comp-math@bbn.com, comp-neuro@smaug.bbb.caltech.edu, connectionists@cs.cmu.edu, cvnet@skivs.ski.org, cybsys-l@bingvmb.cc.binghamton.edu, issnnet-mlist@CNS.BU.EDU, ml@ics.uci.edu, mpsych-l@brownvm.brown.edu, neuron@cattell.psych.upenn.edu, nycvisionpeople@robocop.nyu.edu, psyc@pucc.PRINCETON.EDU, sd3d@franklin.sdsc.edu, self-org@mc.lcs.mit.edu, vision-list@ads.com, visres-cortical@mailbase.ac.uk Subject: Paper available: Neural Model of Visual Stereomatching Paper available in http://www.cs.unc.edu/Research/brainlab/index.html "NEURAL MODEL OF VISUAL STEREOMATCHING: SLANT, TRANSPARENCY, AND CLOUDS" JONATHAN A. MARSHALL, GEORGE J. KALARICKAL, ELIZABETH B. GRAVES Department of Computer Science, CB 3175, Sitterson Hall University of North Carolina, Chapel Hill, NC 27599-3175, U.S.A. marshall@cs.unc.edu, +1-919-962-1887, fax +1-919-962-1799 Stereomatching of oblique and transparent surfaces is described using a model of cortical binocular "tuned" neurons selective for disparities of individual visual features and neurons selective for the position, depth, and 3-D orientation of local surface patches. The model is based on a simple set of learning rules. In the model, monocular neurons project excitatory connection pathways to binocular neurons at appropriate disparities. Binocular neurons project excitatory connection pathways to appropriately tuned "surface patch" neurons. The surface patch neurons project reciprocal excitatory connection pathways to the binocular neurons. Anisotropic intralayer inhibitory connection pathways project between neurons with overlapping receptive fields. The model's responses to simulated stereo image pairs depicting a variety of oblique surfaces and transparently overlaid surfaces are presented. For all the surfaces, the model (1) assigns disparity matches and surface patch representations based on global surface coherence and uniqueness, (2) permits coactivation of neurons representing multiple disparities within the same image location, (3) represents oblique slanted and tilted surfaces directly, rather than approximating them with a series of frontoparallel steps, (4) assigns disparities to a cloud of points at random depths, like human observers, and unlike Prazdny's (1985) method, and (5) causes globally consistent matches to override greedy local matches. The model represents transparency, unlike the Marr and Poggio (1976) model, and it assigns unique disparities, unlike Prazdny's (1985) model. In press, to appear in Network: Computation in Neural Systems, 11/96. From sylee@eekaist.kaist.ac.kr Wed Oct 30 12:01:13 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 MAA16574 for ; Wed, 30 Oct 1996 12:01:03 -0600 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 MAA15274 for ; Wed, 30 Oct 1996 12:00:59 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa07674; 30 Oct 96 10:07:02 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa07672; 30 Oct 96 9:54:57 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa22972; 30 Oct 96 9:53:55 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ac21093; 30 Oct 96 9:05:44 EST Received: from [143.248.141.5] by EDRC.CMU.EDU id aa08683; 30 Oct 96 7:33:39 EST Received: (from sylee@localhost) by eekaist.kaist.ac.kr (8.6.12h2/8.6.12) id VAA14099; Wed, 30 Oct 1996 21:32:58 +0900 Date: Wed, 30 Oct 1996 21:32:58 +0900 From: "prof. Soo-Young Lee" Message-Id: <199610301232.VAA14099@eekaist.kaist.ac.kr> To: cogneuro@ptolemy-ethernet.arc.nasa.gov, comp-neuro@bbb.caltech.edu, connectionists@cs.cmu.edu, genetic-programming@cs.stanford.edu, hybrid-list@cs.ua.edu, ml@ics.uci.edu Subject: Neural Networks Session at SCI'97, Venezuela Content-Length: 6886 CALL FOR PAPERS SCI'97 Neural Networks Session at WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS Caracas, Venezuela July 7-11, 1997 I was asked to organize session(s) on neural networks at a multi-disciplinary conference, SCI'97. As you may see at the following announcements of the conference, it is a truly interdiciplinary conference covering intelligent computing, information theory, cybernetics, social systems, psychology, biology, and applications. WE believe this interdisciplinary conference will provide a very good chance to meet researchers from different-but-related disciplines and promote interesting discussions. Therefore, I would like to invite you to present your recent research results at this conference, and meet interesting people. The Neural Networks sessions will cover following topics: * Neural network models (biological and artificial) * Hybrid systems (Neuro, fuzzy, GA, EP, etc.) * Applications (Speech, Time-series, controls, etc.) * Artificiasl life If you are interested in this multidisciplinary conference, please send me an e-mail to sylee@eekaist.kaist.ac.kr. SUBMISSIONS AND DEADLINES January 17, 1997 Submission of extended abstracts or a condensed first draft(500-1500 words) March 10, 1997 Acceptance notifications May 12, 1997 Submission of papers camera/ready, hard copies and electronic versions Best regards, Soo-Young Lee ********************************************************************** WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS Caracas, Venezuela July 7-11, 1997 MAJOR THEMES Conceptual Infrastructure of Systemics, Cybernetics and Informatics Information Systems (ISAS '97) Control Systems Managerial/Corporative Systems Human Resources Systems Natural Resources Systems Social Systems Educational Systems Financial Systems SCI in Psychology, Cognition and Spirituality SCI in Biology and Medicine SCI in Art Globalization, Development and Emerging Economies ACADEMIC AND SCIENTIFIC SPONSORS World Organization of Systemics and Cybernetics (WOSC) (France) IFSR: International Federation for Systems Research (Austria/USA) International Systems Institute (USA) CUST, Engineer Science Institute of the Blaise Pascal University (France) The International Institute for Advanced Studies in Systems Research and Cybernetics (Canada) Society Applied Systems Research (Canada) Cybernetics and Human Knowing: A Journal of Second Order Cybernetics and Cybersemiotics (Denmark) International Institute of Informatics and Systemics (USA) IEEE (Venezuela Chapter) Simon Bolivar University (Venezuela) Universidad Central de Venezuela INCLUSION OF SCI'97 PROCEEDINGS IN A CD-ROM EXTENDED ENCYCLOPEDIA An electronic version of the SCI 97 proceedings will also be available on CD-ROM, with search and hypertext features. Other media, such as sound, animation and video, are also being considered. These proceedings will also be included in the CD-ROM Extended Encyclopedia of Systemics and Cybernetics (TM), whose development in presently in progress. TYPES OF SUBMISSIONS ACCEPTED Research, Review or Position Papers Panel Presentation, Workshop and/or Round Table Proposals New Topics Proposal (which should include a minimum of 15 papers) Focus Symposia (which should include a minimum of 15 papers) JOURNALS PUBLICATIONS FOR BEST PAPERS Best papers will be published by "Cybernetics and Human Knowing: A Journal of Second Order Cybernetics and Cybersemiotics". Members of the Program Committee who are refrees of the Journal will take the decision on the issue. Other Journals are being considered for other areas of SCI'97/ISAS'97. WEB SITE http://www.callaos.com/SCI 97 PURPOSE The purpose of the Conference is to bring together, from universities and corporations, academics and professionals, researchers and consultants, scientists and engineers, theoreticians and practitioners, all over the world to discuss themes of the conference and to participate with original ideas or innovations, knowledge or experience, theories or methodologies, in the areas of Systemics, Cybernetics and Informatics (SCI). Systemics, Cybernetics and Informatics (SCI) are being increasingly related to each other and to almost every scientific discipline and human activity. Their common transdisciplinarity characterizes and communicates them, generating strong relations among them and with other disciplines. They interpenetrate each other integrating a whole that is permeating human thinking and practice. This phenomenon induced the Organization Committee to structure SCI'97 as a multiconference where participants may focus on an area, or on a discipline, while maintaining open the possibility of attending conferences from other areas or disciplines. This systemic approach stimulates cross-fertilization among different disciplines, inspiring scholars, generating analogies and provoking innovations; which, after all, is one of the very basic principles of the systems movement and a fundamental aim in cybernetics. BACKGROUND The success achieved in ISAS'95 (Information Systems Analysis and Synthesis) held in Baden-Baden (Germany), symbolized by the award granted by the International Institute for Advanced Studios in Systems Research and Cybernetics (Canada), as the best and largest symposium at the 5th International Conference on Systems Research, Informatics and Cybernetics, encouraged its sponsors and session chairs to organize ISAS '96 at Orlando and prepare a more general Conference on Systemics, Cybernetics and Informatics (SCI '97) at Caracas (Venezuela). The widely acknowledged success of ISAS'96 (held on July 22-26 at Orlando) by means of spontaneous verbal feedback and a written comprehensive evaluation from 143 authors, of high quality papers, from 32 countries, galvanized the Program and Organizing Committees to make a definitive commitment to organize SCI'97 and ISAS '97 at Caracas, in July 7-11, 1997. Many Program and Organizing Committees members from past international and world conferences are joining us for SCI '97 and ISAS'97, including most of those who organized the World Conference on Systems Sponsored by UNESCO and the United Nations' World Federation of Engineering Organizations (WFEO). We are still looking for more organizational support from experienced scholars, consultants, practitioners, professionals and researchers, as well as from international or national organizations, public or private, academic or professional. From pauer@igi.tu-graz.ac.at Wed Oct 30 23:51:43 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 XAA01522 for ; Wed, 30 Oct 1996 23:51:39 -0600 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 XAA27624 for ; Wed, 30 Oct 1996 23:51:37 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa08319; 30 Oct 96 23:23:20 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa08317; 30 Oct 96 23:07:20 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23534; 30 Oct 96 23:07:14 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa04310; 30 Oct 96 20:26:29 EST Received: from figiss01.tu-graz.ac.at by EDRC.CMU.EDU id aa13013; 30 Oct 96 20:26:03 EST Received: by figiss01.tu-graz.ac.at id AA06439 (5.67c/IDA-1.5t for Connectionists@CS.CMU.EDU); Thu, 31 Oct 1996 02:22:06 +0100 Date: Thu, 31 Oct 1996 02:22:06 +0100 Message-Id: <199610310122.AA06439@figiss01.tu-graz.ac.at> From: Peter Auer To: Connectionists@cs.cmu.edu Subject: Special Issue on Computational Learning Theory Call for Papers Special Issue of Algorithmica on Computational Learning Theory Expected publication date: Fall 1997 Submission deadline: January 31, 1997 Guest editors: Peter Auer and Wolfgang Maass Besides constructing mathematical theories for Machine Learning, Computational Learning Theory analyses learning algorithms, tries to identify the necessary and sufficient amount of information required for learning, and investigates the computational complexity of learning problems. For this special issue of Algorithmica we are looking for high quality papers addressing topics such as * design and analysis of learning algorithms, * complexity of learning, * mathematical models of learning, * supervised and unsupervised learning on neural nets * theory of (statistical) pattern recognition * ... (suitable topics are not limited to this short list). Submitted papers will go through the usual refereeing process of Algorithmica. Authors should either send four copies of their paper to Peter Auer Institute for Theoretical Computer Science University of Technology, Graz Klosterwiesgasse 32/2 A-8010 Graz Austria or send their paper electronically as postscript or latex file to silt@igi.tu-graz.ac.at. Submissions should be formated accordingly to the following instructions. Manuscripts should be typed on only one side of the page with wide margins. The title page of the article should include all the authors' affiliations and the mailing address, phone, and fax numbers, and the email address of the corresponding author, 5-10 key words, and a detailed abstract emphasizing the main contribution of the paper. Footnotes other than those referring to the title or author affiliation should be avoided. If they are essential, they should be numbered consecutively and listed on a separate page, following the text. If you are planning to submit a paper to the special issue we would like you to send us a short note (silt@igi.tu-graz.ac.at), so that we are able to plan ahead more easily. This and and eventually updated information can also be found at http://www.cis.tu-graz.ac.at/igi/pauer/silt.html. Requests can be sent to silt@igi.tu-graz.ac.at. Peter Auer and Wolfgang Maass From piola@di.unito.it Thu Oct 31 06:46:54 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 GAA03313 for ; Thu, 31 Oct 1996 06:46:49 -0600 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 GAA00477 for ; Thu, 31 Oct 1996 06:46:46 -0600 Received: from (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA10948; Thu, 31 Oct 1996 17:43:11 +0800 Message-Id: <199610310943.RAA10948@cs.uwa.oz.au> From: piola@di.unito.it (Roberto Piola) To: reinforce@cs.uwa.edu.au, ga-list@aic.nrl.navy.mil, hybrid-list@cs.ua.edu, alife@cognet.ucla.edu, EP-LIST@magenta.me.fau.edu, agents@sun.com, machine-learning@eecs.wsu.edu Date: Tue, 29 Oct 1996 11:31:13 +0100 (MET) Sorry if you get multiple copies of this message We are currently working on extending to a Virtual Reality scenario our previous work on Reinforcement Learning; in doing so, we would need a good 3D graphics library for C or C++ languages. We tried, with unsatisfactory results, the following ones: * Portable Dore' 6.01: it simply does not compile under our SunOS installation * Microcosm: it is too slow for doing real-time animations * X3d 2.2: it produces only wire-frame views, and without hidden-line removal * tagl 2.1: perhaps the best one, it lacks only the possibility of changing the point of view of the observer If anyone is currently using a graphic library for representing agents moving in a simulated 3D world, a reference would be greatly appreciated. Thanks in advance Roberto Piola Dept. of Computer Science University of Torino (IT) From desilva@mech.ubc.ca Thu Oct 31 07:14:08 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 HAA04106 for ; Thu, 31 Oct 1996 07:13:17 -0600 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 HAA00812 for ; Thu, 31 Oct 1996 07:13:14 -0600 Received: from (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA10953; Thu, 31 Oct 1996 17:43:53 +0800 Message-Id: <199610310943.RAA10953@cs.uwa.oz.au> From: "Dr. C. W. de Silva" To: dang@csa.cs.technion.ac.il Cc: CLASS-L@ccvm.sunysb.edu, IR-L%UCCVMA.BITNET@mitvma.mit.edu, SMDM-L@caligari.dartmouth.edu, ai-medicine@smi.stanford.edu, arpi-all@isx.com, bayes-news@stat.cmu.edu, bisc-group@diva.eecs.berkeley.edu, cneuro@bbb.caltech.edu, cogpsy@cogsci.soton.ac.uk, connectionists@cs.cmu.edu, dbworld@cs.wisc.edu, fuzzy-mail@dbai.tuwien.ac.at, ga-list@aic.nrl.navy.mil, gann-list@cs.cmu.edu, hybrid-list@cs.ua.edu, idss-request@socs.uts.edu.au, intcon@phoenix.ee.unsw.edu.au, mlnet@swi.psy.uva.nl, neuron-request@cattell.psych.upenn.edu, neuron@cattell.psych.upenn.edu, nl-kr@cs.rpi.edu, reinforce@cs.uwa.edu.au, sigart@vaxa.isi.edu Subject: Call For Papers [connectionists] Date: Tue, 29 Oct 1996 10:36:53 -0800 (PST) Dear Colleague, Please consider the following call for papers for a conference and for an associated special issue of a journal. Thank you. Clarence de Silva. (Regional Editor, North America, for the EAAI Journal) ================================= Special Journal Issue on Intelligent Electronic Systems ======================================================= International Conference on Conventional and Knowledge-Based Intelligent Electronic Systems will be held from 21 through 23 May, 1997, in Adelaide, Australia (Conference Chair: L.C. Jain). Several high-quality papers chosen from those accepted for the Conference will be published in a special issue of the International Journal, Engineering Applications of Artificial Intelligence (The International Journal of Intelligent Real-Time Automation). For the special issue, only papers on "Intelligent Electronic Systems" will be considered. For example, fuzzy, neural, rule-based, knowledge-based, and expert control of practical systems in areas such as biomedical engineering, consumer electronics, communication, control, production systems, electronic security, industrial electronics, mechatronics, multimedia, optical electronics, sensor and actuator technology, robotics, and virtual reality would be appropriate. Please submit your complete paper, to be simultaneously considered for both Conference and Journal issue, no later than November 15, 1996 to: Clarence W. de Silva NSERC Professor of Industrial Automation Department of Mechanical Engineering The University of British Columbia 2324 Main Mall Vancouver, BC, CANADA V6T 1Z4 Fax: 604-822-2403 e-mail: desilva@mech.ubc.ca ======================= From dang@csa.CS.Technion.AC.IL Thu Oct 31 08:49:32 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 IAA05394 for ; Thu, 31 Oct 1996 08:49:26 -0600 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 IAA01839 for ; Thu, 31 Oct 1996 08:49:22 -0600 Received: from (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id RAA10928; Thu, 31 Oct 1996 17:40:58 +0800 Message-Id: <199610310940.RAA10928@cs.uwa.oz.au> From: dang@csa.CS.Technion.AC.IL (Dan Geiger) To: CLASS-L@CCVM.SUNYSB.EDU, IR-L%UCCVMA.BITNET@mitvma.mit.edu, SMDM-L@caligari.Dartmouth.EDU, ai-medicine@SMI.Stanford.EDU, arpi-all@isx.com, bayes-news@STAT.CMU.EDU, bisc-group@diva.eecs.berkeley.edu, cneuro@bbb.caltech.edu, cogpsy@cogsci.soton.ac.uk, connectionists@cs.cmu.edu, dbworld@cs.wisc.edu, fuzzy-mail@dbai.tuwien.ac.at, ga-list@aic.nrl.navy.mil, gann-list@cs.cmu.edu, hybrid-list@cs.ua.edu, idss-request@socs.uts.edu.au, intcon@phoenix.ee.unsw.EDU.AU, mlnet@swi.psy.uva.nl, neuron-request@CATTELL.psych.upenn.edu, neuron@CATTELL.psych.upenn.edu, nl-kr@cs.rpi.edu, reinforce@cs.uwa.edu.au, sigart@vaxa.isi.edu Subject: First Call For Papers [connectionists] Date: Tue, 29 Oct 1996 11:57:19 +0200 ====================================================== C A L L F O R P A P E R S ====================================================== ** U A I 97 ** THE THIRTEENTH ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE August 1-3, 1997 Providence, Rhode Island, USA ======================================= Visit the UAI-97 WWW page at http://cuai97.microsoft.com/ CALL FOR PAPERS 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 the 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. We encourage submissions of papers for UAI-97 that report on advances in the core areas of representation, inference, learning, and knowledge acquisition, as well as on insights derived from building or using applications of uncertain reasoning. We also call for submissions of statements of open problems of wide interest for a discussion in a plenary session (see details below). Topics of interest include (but are not limited to): >> Foundations * Theoretical foundations of uncertain belief and decision * Uncertainty and models of causality * Representation of uncertainty and preference * Generalization of semantics of belief * Conceptual relationships among alternative calculi * Models of confidence in model structure and belief >> Principles and Methods * Planning under uncertainty * Temporal reasoning * Markov processes and decisions under uncertainty * Qualitative methods and models * Automated construction of decision models * Abstraction in representation and inference * Representing intervention and persistence * Uncertainty and methods for learning and data mining * Computation and action under limited resources * Control of computational processes under uncertainty * Time-dependent utility and time-critical decisions * Uncertainty and economic models of problem solving * Integration of logical and probabilistic inference * Statistical methods for automated uncertain reasoning * Synthesis of Bayesian and neural net techniques * Algorithms for uncertain reasoning * Advances in diagnosis, troubleshooting, and test selection >> Empirical Study and Applications * Empirical validation of methods for planning, learning, and diagnosis * Enhancing the human--computer interface with uncertain reasoning * Uncertain reasoning in embedded, situated systems (e.g., softbots) * Automated explanation of results of uncertain reasoning * Nature and performance of architectures for real-time reasoning * Experimental studies of inference strategies * Experience with knowledge-acquisition methods * Comparison of repres. and inferential adequacy of different calculi * Uncertain reasoning and information retrieval For papers focused on applications in specific domains, we suggest that the following issues be addressed in the submission: - Why was it necessary to represent uncertainty in your domain? - What are the distinguishing properties of the domain and problem? - What kind of uncertainties does your application address? - Why did you decide to use your particular uncertainty formalism? - What theoretical problems, if any, did you encounter? - What practical problems did you encounter? - Did users/clients of your system find the results useful? - Did your system lead to improvements in decision making? - What approaches were effective (ineffective) in your domain? - What methods were used to validate the effectiveness of the systems? ================================= SUBMISSION AND REVIEW OF PAPERS ================================= Papers submitted for review should represent original, previously unpublished work (details on policy on submission uniqueness are available at the UAI 97 www homepage). Submitted papers will be evaluated on the basis of originality, significance, technical soundness, and clarity of exposition. Papers may be accepted for presentation in plenary or poster sessions. All accepted papers will be included in the Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence, published by Morgan Kaufmann Publishers. An outstanding student paper will be selected for special distinction. Submitted papers must be at most 20 pages of 12pt Latex article style or equivalent (about 4500 words). See the UAI-97 homepage for additional details about UAI submission policies. We strongly encourage the electronic submission of papers. To submit a paper electronically, send two email messages to the program chairs at uai97@cs.technion.ac.il The first message includes the following information (in this order): * Paper title (plain text) * Author names, including student status (plain text) * Surface mail and Email address for a contact author (plain text) * A short abstract including keywords or topic indicators (plain text) The second message includes an electronic version of the paper (Postscript format). The subject line of the second message should be: $.ps, where $ is an identifier created from the last name of the first author, followed by the first initial of the author's first name. Multiple submissions by the same first author should be indicated by adding a number (e.g., pearlj2.ps) to the end of the identifier. Authors will receive electronic confirmation of the successful receipt of their articles. Authors unable to submit papers electronically should send the first four items electronically to the email address above, and 5 copies of the complete paper to one of the Program Chairs at the addresses listed below. ================================= SUBMISSION OF CHALLENGING PROBLEMS ================================= This year we plan to hold an experimental plenary session entitled "Challenging Problems in Uncertain Reasoning" to discuss critical open problems. We request that interested researchers submit a description of a critical open problem of wide interest that they consider relevant to UAI (according to the guidelines for regular papers). The submission should include a clear unambiguous statement of the problem, ideas on possible solutions, and a survey of the relevant literature where applicable. The statement should be no more than four pages in length. Problems selected by the program chairs will be presented in a plenary session. For each problem selected, the author will give a concise presentation of the problem and its prospective solutions. Following the brief presentations, there will be open discussion of the problem and potential solutions with the entire audience. Although the Challenging Problems will not appear in the proceedings, proposals will be posted on the UAI '97 web pages by May 15 to allow participants to study them and to interact with the authors. ++++++++++++++++++++++++++++++ Important Dates ++++++++++++++++++++++++++++++ >> All submissions must be received by: Feb 23, 1997 >> Notification of acceptance on or before: April 11, 1997 >> Camera-ready copy due: May 9, 1997 ========================== Program Cochairs (submissions and program inquiries): ================= Dan Geiger Computer Science Department Technion, Israel Institute of Technology, Haifa, 32000, Israel Phone: 972 4 829 4265 Fax: 972 4 8221128 Email: dang@cs.technion.ac.il Prakash P. Shenoy University of Kansas School of Business Summerfield Hall Lawrence, KS 66045-2003 USA Phone: (913) 864-7551 Fax: (913) 864-5328 Email: pshenoy@ukans.edu WWW: http://stat1.cc.ukans.edu/~pshenoy General Conference Chair (general conference inquiries): ======================== Eric Horvitz Decision Theory and Adaptive Systems Group Microsoft Research, 9S Redmond, WA 98052 USA Phone: (206) 936 2127 Fax: (206) 936 0502 Email: horvitz@microsoft.com WWW: http://www.research.microsoft.com/research/dtg/horvitz/ ================================================= UAI-97 will occur right after AAAI-97 and will be held in close proximity to AAAI-97. * * * Refer to the UAI-97 WWW home page for late-breaking information: http://cuai97.microsoft.com/ From biehl@physik.uni-wuerzburg.de Thu Oct 31 12:01:13 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 MAA08462 for ; Thu, 31 Oct 1996 12:01:00 -0600 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 MAA05454 for ; Thu, 31 Oct 1996 12:00:58 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa09081; 31 Oct 96 10:49:14 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa09078; 31 Oct 96 10:34:54 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa24115; 31 Oct 96 10:34:13 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa11548; 31 Oct 96 5:58:14 EST Received: from wptx01.physik.uni-wuerzburg.de by EDRC.CMU.EDU id aa14979; 31 Oct 96 5:57:35 EST Received: (from smap@localhost) by wptx01.physik.uni-wuerzburg.de (8.7.5/8.7.3/TPhys_S) id LAA05317 for ; Thu, 31 Oct 1996 11:56:34 +0100 (MEZ) From: Michael Biehl Received: from wptx08.physik.uni-wuerzburg.de(132.187.40.8) by wptx01.physik.uni-wuerzburg.de (smap V1.3) id sma005313 for ; Thu Oct 31 11:56:21 1996 Received: (from biehl@localhost) by wptx08.physik.uni-wuerzburg.de (8.7.5/8.7.3/TPhys_C) id LAA00749 for Connectionists@cs.cmu.edu; Thu, 31 Oct 1996 11:56:20 +0100 (MEZ) Message-Id: <199610311056.LAA00749@wptx08.physik.uni-wuerzburg.de> Subject: paper available: On-line competitive learning To: Connectionists Date: Thu, 31 Oct 1996 11:56:19 +0100 (MEZ) X-Mailer: ELM [version 2.4 PL24 ME8b] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit FTP-host: ftp.physik.uni-wuerzburg.de FTP-filename: /pub/preprint/1996/WUE-ITP-96-025.ps.gz The following manuscript is now available via anonymous ftp: (See below for the retrieval procedure) ------------------------------------------------------------------ "Dynamics of On-line Competitive Learning" Michael Biehl, Ansgar Freking, and Georg Reents Ref: WUE-ITP-96-025 Abstract We present a solvable model of unsupervised competitive learning, which determines prototype vectors suitable for the representation of high--dimensional data. In the thermodynamic limit, the dynamics of on--line training is described exactly by a system of coupled first order differential equations for a set of order parameters. As an example application of the formalism we discuss the identi- fication of two prototypes in the case of two overlapping clusters of data. This specific model exhibits non--trivial behavior like almost stationary plateau configurations which correspond to weakly repulsive fixed points of the dynamics. The ability of the system to escape from this fixed point as well as its asymptotic behavior depend critically on the learning rate used in the algorithm. --------------------------------------------------------------------- Retrieval procedure: unix> ftp ftp.physik.uni-wuerzburg.de Name: anonymous Password: {your e-mail address} ftp> cd pub/preprint/1996 ftp> binary ftp> get WUE-ITP-96-025.ps.gz (*) ftp> quit unix> gunzip WUE-ITP-96-025.ps.gz e.g. unix> lp WUE-ITP-96-025.ps [8 pages] (*) can be replaced by "get WUE-ITP-96-025.ps". The file will then be uncompressed before transmission (slow!). _____________________________________________________________________ -- Michael Biehl Institut fuer Theoretische Physik Julius-Maximilians-Universitaet Wuerzburg Am Hubland D-97074 Wuerzburg email: biehl@physik.uni-wuerzburg.de homepage: http://www.physik.uni-wuerzburg.de/~biehl Tel.: (+49) (0)931 888 5865 " " " 5131 Fax : (+49) (0)931 888 5141