From wray@Heuristicrat.COM Wed Oct 25 19:11:43 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 25 Oct 95 19:11:41 -0500; AA00856 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 25 Oct 95 19:11:39 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15791; 25 Oct 95 18:46:06 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14187; 24 Oct 95 1:17:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12214; 24 Oct 95 1:16:55 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa16594; 23 Oct 95 20:33:23 EDT Received: from Heuristicrat.COM by EDRC.CMU.EDU id aa26818; 23 Oct 95 20:32:53 EDT Received: (smap@localhost) by Heuristicrat.COM (8.6.11/8.6.5) id RAA24599 for ; Mon, 23 Oct 1995 17:32:48 -0700 Received: from euclid.heuristicrat.com(199.171.121.3) by Heuristicrat.COM via smap (V1.3) id sma024597; Mon Oct 23 17:32:36 1995 Received: from shattuck.Heuristicrat.COM by euclid.Heuristicrat.COM (4.1/Othar) id AA28178; Mon, 23 Oct 95 17:32:35 PDT Date: Mon, 23 Oct 95 17:32:35 PDT From: Wray Buntine Message-Id: <9510240032.AA28178@euclid.Heuristicrat.COM> To: connectionists@cs.cmu.edu Subject: ISIS: Information, Statistics and Induction in Science *** CALL FOR PAPERS *** ISIS: Information, Statistics and Induction in Science Melbourne, Australia, 20-23 August 1996 Conference Chair: David Dowe Co-chairs: Kevin Korb and Jonathan Oliver INVITED SPEAKERS: Henry Kyburg, Jr. (University of Rochester, NY) J. Ross Quinlan (Sydney University) Jorma J. Rissanen (IBM Almaden Research, San Jose, California) Ray Solomonoff (U.S.A.) PROGRAM COMMITTEE: Lloyd Allison, Mark Bedau, Hamparsum Bozdogan, Wray Buntine, Peter Cheeseman, Honghua Dai, David Dowe, Doug Fisher, Alex Gammerman, Clark Glymour, Randy Goebel, David Hand, Bill Harper, David Heckerman, Colin Howson, Lawrence Hunter, Frank Jackson, Max King, Kevin Korb, Henry Kyburg, Ming Li, Nozomu Matsubara, Aleksandar Milosavljevic, Richard Neapolitan, Jonathan Oliver, Michael Pazzani, J. Ross Quinlan, Glenn Shafer, Peter Slezak, Ray Solomonoff, Paul Thagard, Neil Thomason, Raul Valdes-Perez, Tim van Gelder, Paul Vitanyi, Chris Wallace, Geoff Webb, Xindong Wu, Jan Zytkow. Inquiries to: isis96@cs.monash.edu.au David Dowe: dld@cs.monash.edu.au Kevin Korb: korb@cs.monash.edu.au or Jonathan Oliver: jono@cs.monash.edu.au Information is available on the WWW at: http://www.cs.monash.edu.au/~jono/ISIS/ISIS.shtml This conference will explore the use of computational modelling to understand and emulate inductive processes in science. The problems involved in building and using such computer models reflect methodological and foundational concerns common to a variety of academic disciplines, especially statistics, artificial intelligence (AI) and the philosophy of science. This conference aims to bring together researchers from these and related fields to present new computational technologies for supporting or analysing scientific inference and to engage in collegial debate over the merits and difficulties underlying the various approaches to automating inductive and statistical inference. AREAS OF INTEREST. The following streams/subject areas are of particular interest to the organisers: Concept Formation and Classification. Minimum Encoding Length Inference Methods. Scientific Discovery. Theory Revision. Bayesian Methodology. Foundations of Statistics. Foundations of Social Science. Foundations of AI. CALL FOR PAPERS. Prospective authors should mail five copies of their papers to Dr. David Dowe, ISIS chair. Alternatively, authors may submit by email to isis96@cs.monash.edu.au. Email submissions must be in LaTex (using the ISIS style guide [will be available at the ISIS WWW page]). Submitted papers should be in double-column format in 10 point font and not exceeding 10 pages. An additional page should display the title, author(s) and affiliation(s), abstract, keywords and identification of which of the eight areas of interest (see http://www.cs.monash.edu.au/~jono/ISIS/ISIS.Area.Interest.html) are most relevant to the paper. Refereeing will be blind; that is, this additional page will not be passed along to referees. The proceedings will be published; details have not yet been settled with the prospective publisher. Accepted papers will have to be represented by at least one author in attendance to be published. Papers should be sent to: Dr David Dowe ISIS chair Department of Computer Science Monash University Clayton Victoria 3168 Australia Phone: +61-3-9 905 5226 FAX: +61-3-9 905 5146 Email: isis96@cs.monash.edu.au Submission (receipt) deadline: 11 March, 1996 Notification of acceptance: 10 June, 1996 Camera-ready copy (receipt) deadline: 15 July, 1996 CONFERENCE VENUE ISIS will be held at the Old Melbourne Hotel, 5-17 Flemington Rd. North Melbourne. The Old Melbourne Hotel is within easy walking distance of downtown Melbourne, Melbourne University, many restaurants (on Lygon Street) and the Melbourne Zoo. It is about fifteen to twenty minutes drive from the airport. REGISTRATION A registration form will be available at the WWW site http://www.cs.monash.edu.au/~jono/ISIS/ISIS.shtml, or by mail from the conference chair. Dates for registration will be considered to be met assuming that legible postmarks are on or before the dates and airmail is used. Student registrations will be available at a discount (but prices have not yet been fixed). Relevant dates are: Early registration (at a discount): 3 June, 1996 Final registration: 1 July, 1996 From andreas@sabai.cs.colorado.edu Wed Oct 25 20:27:29 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 25 Oct 95 20:27:26 -0500; AA01461 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 25 Oct 95 20:27:23 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15796; 25 Oct 95 18:46:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab14187; 24 Oct 95 1:17:32 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12219; 24 Oct 95 1:17:08 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa18708; 24 Oct 95 0:16:52 EDT Received: from sabai.cs.Colorado.EDU by RI.CMU.EDU id aa16962; 24 Oct 95 0:15:22 EDT Received: (from andreas@localhost) by sabai.cs.colorado.edu (8.6.12/8.6.12) id WAA28537; Mon, 23 Oct 1995 22:14:31 -0600 From: Andreas Weigend Message-Id: <199510240414.WAA28537@sabai.cs.colorado.edu> Subject: Noisy Time Series (2-day NIPS workshop) To: Connectionists@cs.cmu.edu Date: Mon, 23 Oct 1995 22:14:30 -0600 (MDT) Cc: yaser@cs.caltech.edu, andreas@cs.colorado.edu X-Mailer: ELM [version 2.4 PL23] Content-Type: text Content-Length: 3025 First announcement of the following workshop. Updates and call for presentations is on the web page. ________________________________________________________________________ NOISY TIME SERIES NIPS-95 Workshop: Dec 1 and 2, 1995 Organizers: Yaser Abu-Mostafa and Andreas Weigend -> Full information via http://www.cs.colorado.edu/~andreas/Home.html <- Focus of the workshop: Noisy time series is an application domain that presents unique challenges to neural networks and other learning techniques. Even without the noise as a factor, a practical time series suffers from non-stationarity, alternating between different regimes, and behaving differently at different time scales. The high level of noise in many time series complicates matters further by impeding learning and by amplifying the problems of overfitting and local minima. This workshop addresses the theory and techniques for dealing with these issues and uses real-life examples of time series to illustrate the main ideas. If you would like to contribute, please send by November 15, 1995 your abstract to yaser@cs.caltech.edu and andreas@cs.colorado.edu Some of the talks of this workshop will be encouraged for submission to a special issue on Noisy Time Series of the International Journal of Neural Systems (World Scientific; with submission deadline 1/31/96) Currently scheduled and confirmed talks: 1. Andreas Weigend: Overview talk: Modeling, Learning, and Meaning of Noisy Time Series 2. Yaser Abu-Mostafa: Validation of Volatility Models 3. Yoshua Bengio: Multi-Scale Temporal Models for long-term Dependencies 4. Vance Bjorn: Waveperts: Multiresolution Feature Extraction and Prediction of Time-Series 5. Peter J. Bolland and Jerry T. Connor: Robust Non-Linear Multivariate Kalman Filter for Arbitrage Identification 6. Mark Craven: Understanding Time-Series Networks: A Case Study in Rule Extraction 7. John Moody: Toward Minimal Prediction Risk: Model Selection and Construction Strategies for Noisy Time Series Problems 8. Barak A. Pearlmutter: Statistical Limits to Learning Temporal Structure 9. Ashok N. Srivastava: Improved Time Series Segmentation using Gated Experts with Simulated Annealing 10. Halbert White: Neural Network Methods For Estimating Higher Order Moments In Time Series 11. Hans Georg Zimmermann: Neuro versus Neuro Fuzzy Models in Economics ________________________________________________________________________ Andreas Weigend Computer Science Department office phone: (303) 492-2524 University of Colorado Box 430 fax: (303) 492-2844 Boulder, CO 80309-0430 secretary: (303) 492-7514 USA ________________________________________________________________________ From Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU Thu Oct 26 16:33:35 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:33 -0500; AA17410 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:31 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa16231; 26 Oct 95 0:11:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa16228; 26 Oct 95 0:03:30 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14332; 26 Oct 95 0:02:22 EDT Received: from DST.BOLTZ.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa21160; 25 Oct 95 23:58:13 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14310; 25 Oct 95 23:57:35 EDT To: Connectionists@cs.cmu.edu Reply-To: Dave_Touretzky@cs.cmu.edu Subject: problem fixed re: Connectionists list Date: Wed, 25 Oct 95 23:57:34 -0400 Message-Id: <14308.814679854@DST.BOLTZ.CS.CMU.EDU> From: Dave_Touretzky@DST.BOLTZ.CS.CMU.EDU This past week we had a problem with the processing of the distribution list used for CONNECTIONSTS. As a result, several messages didn't get sent out to subscribers. The problem has been corrected, and we are now redistributing the messages that we believe got eaten. Apologies to anyone who receives a duplicate copy. -- Dave Touretzky & Lisa Saksida From jagota@ponder.csci.unt.edu Thu Oct 26 16:33:40 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:38 -0500; AA17416 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:34 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab16231; 26 Oct 95 0:12:10 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab16228; 26 Oct 95 0:03:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14336; 26 Oct 95 0:02:43 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa02092; 17 Oct 95 13:11:24 EDT Received: from ponder.csci.unt.edu by EDRC.CMU.EDU id aa27628; 17 Oct 95 13:10:32 EDT Received: by ponder (5.61/1.36) id AA08474; Tue, 17 Oct 95 12:10:48 -0500 Date: Tue, 17 Oct 95 12:10:48 -0500 From: Jagota Arun Kumar Message-Id: <9510171710.AA08474@ponder> To: connectionists@cs.cmu.edu Subject: NIPS*95 workshop on Optimization Dear Connectionists: Attached find a description of the NIPS*95 workshop on optimization. For up-to-date information, including abstracts of talks, see the URL. We might be able to fit in one or two more talks. Send me a title and abstract by e-mail if you'd like to give a talk. Arun Jagota ---------------------------------------------------------------------- OPTIMIZATION PROBLEM SOLVING WITH NEURAL NETS NIPS95 Workshop, Organizer: Arun Jagota Friday Dec 1 1995, 7:30--9:30 AM and 4:30--6:30 PM E-mail: jagota@cs.unt.edu Workshop URL: http://www.msci.memphis.edu/~jagota/NIPS95 Ever since the work of Hopfield and Tank, neural nets have found increasing use in the approximate solution of difficult optimization problems, arising in many applications. Such neural nets are well-suited in principle to these problems, because they minimize, in parallel form, an energy function into which an optimization problem's objective and constraints can be mapped. Unfortunately, often they haven't worked well in practice, for two reasons. First, mapping the objective and constraints of a problem onto a single good energy function has turned out difficult for certain problems, for example for the Travelling Salesman Problem. The ease or difficulty of mapping has turned out moreover to be problem-dependent, making it difficult to find a good general mapping methodology. Second, the dynamical algorithms have often been limited to some form of local search or gradient-descent. In recent years, there have been significant advances on both fronts. Provably good mappings of several optimization problems have been found. Powerful dynamical algorithms that go beyond gradient-descent have also been developed, with ideas borrowed from different fields. Examples are Mean Field Annealing, Simulated Annealing, Projection Methods, and Randomized Multi-Start Algorithms. This workshop aims to take stock of the state of the art on this topic, and to study directions for future research and applications. Target Audience Both the topics---neural nets and optimization---are of relevance to a wide range of disciplines and we hope that several of these will be represented at this workshop. These include Cognitive Science, Computer Science, Engineering, Mathematics, Neurobiology, Physics, Chemistry, and Psychology. Format 6-8 30 minute talks, each including 5 minutes for discussion. 30 minutes for discussion at the end. Talks The Complexity of Stability in Hopfield Networks Ian Parberry, University of North Texas Title to be announced Anand Rangarajan, Yale University Performance of Neural Network Algorithms for Maximum Clique on Highly Compressible Graphs Arun Jagota, University of North Texas Population-based Incremental Learning Shumeet Baluja, Carnegie-Mellon University How Good are Neural Networks Algorithms for the Travelling Salesman Problem? Marco Budinich, Dipartimento di Fisica, Via Valerio 2, 34127 Trieste ITALY Relaxation Labeling Networks for the Maximum Clique Problem Marcello Pelillo, University of Venice, Italy ---------------------------------------------------------------------- From shawn_mikiten@biad23.uthscsa.edu Thu Oct 26 16:33:48 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:39 -0500; AA17421 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:37 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ac16231; 26 Oct 95 0:12:51 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ac16228; 26 Oct 95 0:03:32 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14340; 26 Oct 95 0:02:47 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa22946; 18 Oct 95 14:56:14 EDT Received: by CS.CMU.EDU id aa04158; 18 Oct 95 14:55:37 EDT Received: from biad23.uthscsa.edu by CS.CMU.EDU id aa04149; 18 Oct 95 14:54:26 EDT Message-Id: Date: 18 Oct 1995 14:03:51 U From: shawn mikiten Subject: BrainMap '95 Conference ann To: Connectionist X-Mailer: Mail*Link SMTP/QM 3.0.0 The upcoming BrainMap '95 Conference on December 3 & 4 will be in San Antonio, TX. Anyone involved in, or interested in developing databases in brain mapping and/or behaviors are welcome to apply. If you have access to WWW the URL is: http://ric.uthscsa.edu/services/95 From robert@fit.qut.edu.au Thu Oct 26 16:33:49 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:42 -0500; AA17424 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:39 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ad16231; 26 Oct 95 0:13:25 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ad16228; 26 Oct 95 0:03:33 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14344; 26 Oct 95 0:02:52 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa22983; 20 Oct 95 2:01:19 EDT Received: from ocean.fit.qut.edu.au by EDRC.CMU.EDU id aa11865; 20 Oct 95 1:58:58 EDT Received: (from robert@localhost) by ocean.fit.qut.edu.au (8.6.12/8.6.12) id PAA25350; Fri, 20 Oct 1995 15:55:04 +1000 Date: Fri, 20 Oct 1995 15:55:04 +1000 Message-Id: <199510200555.PAA25350@ocean.fit.qut.edu.au> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: connectionists@cs.cmu.edu From: Robert Andrews Subject: Rule Extraction From ANNs - AISB96 Workshop X-Mailer: ============================================================= FIRST CALL FOR PAPERS AISB-96 WORKSHOP Society for the Study of Artificial Intelligence and Simulation of Behaviour (SSAISB) University of Sussex, Brighton, England April 2, 1996 -------------------------------------------- RULE-EXTRACTION FROM TRAINED NEURAL NETWORKS -------------------------------------------- Robert Andrews Neurocomputing Research Centre Queensland University of Technology Brisbane 4001 Queensland, Australia Phone: +61 7 864-1656 Fax: +61 7 864-1969 E-mail: robert@fit.qut.edu.au Joachim Diederich Neurocomputing Research Centre Queensland University of Technology Brisbane 4001 Queensland, Australia Phone: +61 7 864-2143 Fax: +61 7 864-1801 E-mail: joachim@fit.qut.edu.au Lee Giles NEC Research Institute 4 Independence Way Princeton, NJ 08540 The objective of the workshop is to provide a discussion platform for researchers interested in Artificial Neural Networks (ANNs), Artificial Intelligence (AI) and Cognitive Science. The workshop should be of considerable interest to computer scientists and engineers as well as to cognitive scientists and people interested in ANN applications which require a justification of a classification or inference. INTRODUCTION It is becoming increasingly apparent that without some form of explanation capability, the full potential of trained Artificial Neural Networks may not be realised. The problem is an inherent inability to explain in a comprehensible form, the process by which a given decision or output generated by an ANN has been reached. For Artificial Neural Networks to gain a even wider degree of user acceptance and to enhance their overall utility as learning and generalisation tools, it is highly desirable if not essential that an `explanation' capability becomes an integral part of the functionality of a trained ANN. Such a requirement is mandatory if, for example, the ANN is to be used in what are termed as `safety critical' applications such as airlines and power stations. In these cases it is imperative that a system user be able to validate the output of the Artificial Neural Network under all possible input conditions. Further the system user should be provided with the capability to determine the set of conditions under which an output unit within an ANN is active and when it is not, thereby providing some degree of transparency of the ANN solution. Craven & Shavlik (1994) define the rule-extraction from neural networks task as follows: "Given a trained neural network and the examples used to train it, produce a concise and accurate symbolic description of the network." The following discussion of the importance of rule-extraction algorithms is based on this definition. THE IMPORTANCE OF RULE-EXTRACTION ALGORITHMS Since rule extraction from trained Artificial Neural Networks comes at a cost in terms of resources and additional effort, an early imperative in any discussion is to delineate the reasons why rule extraction is an important, if not mandatory, extension of conventional ANN techniques. The merits of including rule extraction techniques as an adjunct to conventional Artificial Neural Network techniques include: Data exploration and the induction of scientific theories Over time neural networks have proven to be extremely powerful tools for data exploration with the capability to discover previously unknown dependencies and relationships in data sets. As Craven and Shavlik (1994) observe, `a (learning) system may discover salient features in the input data whose importance was not previously recognised.' However, even if a trained Artificial Neural Network has learned interesting and possibly non-linear relationships, these relationships are encoded incomprehensibly as weight vectors within the trained ANN and hence cannot easily serve the generation of scientific theories. Rule-extraction algorithms significantly enhance the capabilities of ANNs to explore data to the benefit of the user. Provision of a `user explanation' capability Experience has shown that an explanation capability is considered to be one of the most important functions provided by symbolic AI systems. In particular, the salutary lesson from the introduction and operation of Knowledge Based systems is that the ability to generate even limited explanations (in terms of being meaningful and coherent) is absolutely crucial for the user-acceptance of such systems. In contrast to symbolic AI systems, Artificial Neural Networks have no explicit declarative knowledge representation. Therefore they have considerable difficulty in generating the required explanation structures. It is becoming increasingly apparent that the absence of an `explanation' capability in ANN systems limits the realisation of the full potential of such systems and it is this precise deficiency that the rule extraction process seeks to redress. Improving the generalisation of ANN solutions Where a limited or unrepresentative data set from the problem domain has been used in the ANN training process, it is difficult to determine when generalisation can fail even with evaluation methods such as cross-validation. By being able to express the knowledge embedded within the trained Artificial Neural Network as a set of symbolic rules, the rule-extraction process may provide an experienced system user with the capability to anticipate or predict a set of circumstances under which generalisation failure can occur. Alternatively the system user may be able to use the extracted rules to identify regions in input space which are not represented sufficiently in the existing ANN training set data and to supplement the data set accordingly. A CLASSIFICATION SCHEME FOR RULE EXTRACTION ALGORITHMS The method of classification proposed here is in terms of: (a) the expressive power of the extracted rules; (b) the `translucency' of the view taken within the rule extraction technique of the underlying Artificial Neural Network units; (c) the extent to which the underlying ANN incorporates specialised training regimes; (d) the `quality' of the extracted rules; and (e) the algorithmic `complexity' of the rule extraction/rule refinement technique. The `translucency' dimension of classification is of particular interest. It is designed to reveal the relationship between the extracted rules and the internal architecture of the trained ANN. It comprises two basic categories of rule extraction techniques viz `decompositional' and `pedagogical' and a third - labelled as `eclectic' - which combines elements of the two basic categories. The distinguishing characteristic of the `decompositional' approach is that the focus is on extracting rules at the level of individual (hidden and output) units within the trained Artificial Neural Network. Hence the `view' of the underlying trained Artificial Neural Network is one of `transparency'. The translucency dimension - `pedagogical' is given to those rule extraction techniques which treat the trained ANN as a `black box' ie the view of the underlying trained Artificial Neural Network is `opaque'. The core idea in the `pedagogical' approach is to `view rule extraction as a learning task where the target concept is the function computed by the network and the input features are simply the network's input features'. Hence the `pedagogical' techniques aim to extract rules that map inputs directly into outputs. Where such techniques are used in conjunction with a symbolic learning algorithm, the basic motif is to use the trained Artificial Neural Network to generate examples for the learning algorithm. As indicated above the proposed third category in this classification scheme are composites which incorporate elements of both the `decompositional' and `pedagogical' (or `black-box') rule extraction techniques. This is the `eclectic' group. Membership in this category is assigned to techniques which utilise knowledge about the internal architecture and/or weight vectors in the trained Artificial Neural Network to complement a symbolic learning algorithm. An ancillary problem to that of rule extraction from trained ANNs is that of using the ANN for the `refinement' of existing rules within symbolic knowledge bases. The goal in rule refinement is to use a combination of ANN learning and rule extraction techniques to produce a `better' (ie a `refined') set of symbolic rules which can then be applied back in the original problem domain. In the rule refinement process, the initial rule base (ie what may be termed `prior knowledge') is inserted into an ANN by programming some of the weights. The rule refinement process then proceeds in the same way as normal rule extraction viz (1) train the network on the available data set(s); and (2) extract (in this case the `refined') rules - with the proviso that the rule refinement process may involve a number of iterations of the training phase rather than a single pass. DISCUSSION POINTS FOR WORKSHOP PARTICIPANTS 1. Decompositional vs. learning approaches to rule- extraction from ANNs - What are the advantages and disadvantages w.r.t. performance, solution time, computational complexity, problem domain etc. Are decompositional approaches always dependent on a certain ANN architecture? 2. Rule-extraction from trained neural networks vs. symbolic induction. What are the relative strength and weaknesses? 3. What are the most important criteria for rule quality? 4. What are the most suitable representation languages for extracted rules? How does the extraction problem vary across different languages? 5. What is the relationship between rule-initialisation (insertion) and rule-extraction? For instance, are these equivalent or complementary processes? How important is rule-refinement by neural networks? 6. Rule-extraction from trained neural networks and computational learning theory. Is generating a minimal rule-set which mimics an ANN a hard problem? 7. Does rule-initialisation result in faster learning and improved generalisation? 8. To what extent are existing extraction algorithms limited in their applicability? How can these limitations be addressed? 9. Are there any interesting rule-extraction success stories? That is, problem domains in which the application of rule-extraction methods has resulted in an interesting or significant advance. ACKNOWLEDGEMENT Many thanks to Mark Craven, and Alan Tickle for comments on earlier versions of this proposal. RELEVANT PUBLICATIONS Andrews, R Diederich, J and Tickle, A.B.: A survey and critique of techniques for extracting rules from trained artificial neural networks. To appear: Knowledge-Based Systems, 1995 (ftp:fit.qut.edu.au//pub/NRC/ps/QUTNRC-95-01- 02.ps.Z) Andrews, R and Geva, S: `Rule extraction from a constrained error back propagation MLP' Proc. 5th Australian Conference on Neural Networks Brisbane Queensland (1994) pp 9-12 Andrews, R and Geva, S `Inserting and extracting knowledge from constrained error back propagation networks' Proc. 6th Australian Conference on Neural Networks Sydney NSW (1995) Craven, M W and Shavlik , J W `Using sampling and queries to extract rules from trained neural networks' Machine Learning: Proceedings of the Eleventh International Conference (San Francisco CA) (1994) (in print) Diederich, J `Explanation and artificial neural networks' International Journal of Man-Machine Studies Vol 37 (1992) pp 335-357 Fu, L M `Neural networks in computer intelligence' McGraw Hill (New York) (1994) Fu, L M `Rule generation from neural networks' IEEE Transactions on Systems, Man, and Cybernetics Vol 28 No 8 (1994) pp 1114-1124 Gallant, S `Connectionist expert systems' Communications of the ACM Vol 31 No 2 (February 1988) pp 152-169 Giles, C L and Omlin C W `Rule refinement with recurrent neural networks' Proc. of the IEEE International Conference on Neural Networks (San Francisco CA) (March 1993) pp 801-806 Giles, C L and Omlin C W `Extraction, insertion, and refinement of symbolic rules in dynamically driven recurrent networks' Connection Science Vol 5 Nos 3 and 4 (1993) pp 307-328 Giles, C L, Miller, C B, Chen, D, Chen, H, Sun, G Z and Lee, Y C `Learning and extracting finite state automata with second-order recurrent neural networks' Neural Computation Vol 4 (1992) pp 393-405 Hayward, R.; Pop, E.; Diederich, J.: Extracting Rules for Grammar Recognition from Cascade-2 Networks. Proceeding, IJCAI-95 Workshop on Machine Learning and Natural Language Processing. McMillan, C, Mozer, M C and Smolensky, P `The connectionist scientist game: rule extraction and refinement in a neural network' Proc. of the Thirteenth Annual Conference of the Cognitive Science Society (Hillsdale NJ) 1991 Omlin, C W, Giles, C L and Miller, C B `Heuristics for the extraction of rules from discrete time recurrent neural networks' Proc. of the International Joint Conference on Neural Networks (IJCNN'92) (Baltimore MD) Vol 1 (1992) pp 33 Pop, E, Hayward, R, and Diederich, J `RULENEG: extracting rules from a trained ANN by stepwise negation' QUT NRC (December 1994) Sestito, S and Dillon, T `Automated knowledge acquisition of rules with continuously valued attributes' Proc. 12th International Conference on Expert Systems and their Applications (AVIGNON'92) (Avignon France) (May 1992) pp 645-656. Sestito, S and Dillon, T `Automated knowledge acquisition' Prentice Hall (Australia) (1994) Thrun, S B `Extracting Provably Correct Rules From Artificial Neural Networks' Technical Report IAI-TR-93-5 Institut fur Informatik III Universitat Bonn (1994) Tickle, A B, Orlowski, M, and Diederich, J `DEDEC: decision detection by rule extraction from neural networks' QUT NRC (September 1994) Towell, G and Shavlik, J `The Extraction of Refined Rules Tresp, V, Hollatz, J and Ahmad, S `Network Structuring and Training Using Rule-based Knowledge' Advances In Neural Information Processing Vol 5 (1993) pp871-878 SUBMISSION OF WORKSHOP EXTENDED ABSTRACTS/PAPERS Authors are invited to submit 3 copies of either an extended abstract or full paper relating to one of the topic areas listed above. Papers should be written in English in single column format and should be limited to no more than eight, (8) sides of A4 paper including figures and references. Centered at the top of the first page should be complete title, author name(s), affiliation(s), and mailing and email address(es), followed by blank space, abstract(15-20 lines), and text. Please include the following information in an accompanying cover letter: Full title of paper, presenting author's name, address, and telephone and fax numbers, authors e-mail address. Submission Deadline is January 15th,1996 with notification to authors by 31st January,1996. For further information, inquiries, and paper submissions please contact: Robert Andrews Queensland University of Technology GPO Box 2434 Brisbane Q. 4001. Australia. phone +61 7 864-1656 fax +61 7 864-1969 email robert@fit.qut.edu.au More information about the AISB-96 workshop series is available from: ftp: ftp.cogs.susx.ac.uk pub/aisb/aisb96 WWW: (http://www.cogs.susx.ac.uk/aisb/aisb96) WORKSHOP PARTICIPATION CHARGES The workshop fees are listed below. Note that these fees include lunch. Student charges are shown in brackets. AISB NON-ASIB MEMBERS MEMBERS 1 Day Workshop 65 (45) 80 LATE REGISTRATION: 85 (60) 100 PROGRAM COMMITTEE MEMBERS R. Andrews, Queensland University of Technology A. Tickle, Queensland University of Technology S. Sestito, DSTO, Australia J. Shavlik, University of Wisconsin =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Mr Robert Andrews School of Information Systems robert@fit.qut.edu.au Faculty of Information Technology R.Andrews@qut.edu.au Queensland University of Technology +61 7 864 1656 (voice) GPO Box 2434 _--_|\ +61 7 864 1969 (fax) Brisbane Q 4001 / QUT Australia \_.--._/ v =-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= From mpolycar@ece.uc.edu Thu Oct 26 16:33:54 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:46 -0500; AA17437 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:43 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab16250; 26 Oct 95 0:31:39 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab16248; 26 Oct 95 0:24:01 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14366; 26 Oct 95 0:23:43 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa03418; 20 Oct 95 11:11:56 EDT Received: from babbage.ece.uc.edu by RI.CMU.EDU id aa04649; 20 Oct 95 11:11:23 EDT Received: from zoe.ece.uc.edu (mpolycar@zoe.ece.uc.edu [129.137.8.203]) by babbage.ece.uc.edu (8.6.12/8.6.9) with ESMTP id LAA05663; Fri, 20 Oct 1995 11:05:27 -0400 From: Marios Polycarpou Received: (mpolycar@localhost) by zoe.ece.uc.edu (8.6.9/8.6.4) id LAA21722; Fri, 20 Oct 1995 11:05:26 -0400 Message-Id: <199510201505.LAA21722@zoe.ece.uc.edu> Subject: ISIC'96: Call for Papers To: Connectionists@cs.cmu.edu Date: Fri, 20 Oct 1995 11:05:26 -0400 (EDT) X-Mailer: ELM [version 2.4 PL23] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 7192 ************************************ CALL FOR PAPERS 11th IEEE International Symposium on Intelligent Control (ISIC) ************************************  Sponsored by the IEEE Control Systems Society and held in conjunction with The 1996 IEEE International Conference on Control Applications (CCA) and The IEEE Symposium on Computer-Aided Control System Design (CACSD) September 15-18, 1996 The Ritz-Carlton Hotel, Dearborn, Michigan, USA ISIC General Chair: Kevin M. Passino, The Ohio State University ISIC Program Chair: Jay A. Farrell, University of California, Riverside ISIC Publicity Chair: Marios Polycarpou, University of Cincinnati Intelligent control, the discipline where control algorithms are developed by emulating certain characteristics of intelligent biological systems, is being fueled by recent advancements in computing technology and is emerging as a technology that may open avenues for significant technological advances. For instance, fuzzy controllers which provide for a simplistic emulation of human deduction have been heuristically constructed to perform difficult nonlinear control tasks. Knowledge-based controllers developed using expert systems or planning systems have been used for hierarchical and supervisory control. Learning controllers, which provide for a simplistic emulation of human induction, have been used for the adaptive control of uncertain nonlinear systems. Neural networks have been used to emulate human memorization and learning characteristics to achieve high performance adaptive control for nonlinear systems. Genetic algorithms that use the principles of biological evolution and "survival of the fittest" have been used for computer-aided-design of control systems and to automate the tuning of controllers by evolving in real-time populations of highly fit controllers. Topics in the field of intelligent control are gradually evolving, and expanding on and merging with those of conventional control. For instance, recent work has focused on comparative cost-benefit analyses of conventional and intelligent control techniques using simulation and implementations. In addition, there has been recent activity focused on modeling and nonlinear analysis of intelligent control systems, particularly work focusing on stability analysis. Moreover, there has been a recent focus on the development of intelligent and conventional control systems that can achieve enhanced autonomous operation. Such intelligent autonomous controllers try to integrate conventional and intelligent control approaches to achieve levels of performance, reliability, and autonomous operation previously only seen in systems operated by humans. Papers are being solicited for presentation at ISIC and for publication in the Symposium Proceedings on topics such as: - Architectures for intelligent control - Hierarchical intelligent control - Distributed intelligent systems - Modeling intelligent systems - Mathematical analysis of intelligent systems - Knowledge-based systems - Fuzzy systems / fuzzy control - Neural networks / neural control - Machine learning - Genetic algorithms - Applications / Implementations: - Automotive / vehicular systems - Robotics / Manufacturing - Process control - Aircraft / spacecraft This year the ISIC is being held in conjunction with the 1996 IEEE International Conference on Control Applications and the IEEE Symposium on Computer-Aided Control System Design. Effectively this is one large conference at the beautiful Ritz-Carlton hotel. The programs will be held in parallel so that sessions from each conference can be attended by all. There will be one registration fee and each registrant will receive a complete set of proceedings. For more information, and information on how to submit a paper to the conference see the back of this sheet. ++++++++++ Submissions: ++++++++++ Papers: Five copies of the paper (including an abstract) should be sent by Jan. 22, 1996 to: Jay A. Farrell, ISIC'96 College of Engineering ph: (909) 787-2159 University of California, Riverside fax: (909) 787-3188 Riverside, CA 92521 Jay_Farrell@qmail.ucr.edu Clearly indicate who will serve as the corresponding author and include a telephone number, fax number, email address, and full mailing address. Authors will be notified of acceptance by May 1996. Accepted papers, in final camera ready form (maximum of 6 pages in the proceedings), will be due in June 1996. Invited Sessions: Proposals for invited sessions are being solicited and are due Jan. 22, 1996. The session organizers should contact the Program Chair by Jan. 1, 1996 to discuss their ideas and obtain information on the required invited session proposal format. Workshops and Tutorials: Proposals for pre-symposium workshops should be submitted by Jan. 22, 1996 to: Kevin M. Passino, ISIC'96 Dept. Electrical Engineering ph: (614) 292-5716 The Ohio State University fax: (614) 292-7596 2015 Neil Ave. passino@osu.edu Columbus, OH 43210-1272 Please contact K.M. Passino by Jan. 1, 1996 to discuss the content and required format for the workshop or tutorial proposal. ++++++++++++++++++++++++ Symposium Program Committee: ++++++++++++++++++++++++ James Albus, National Institute of Standards and Technology Karl Astrom, Lund Institute of Technology Matt Barth, University of California, Riverside Michael Branicky, Massachusetts Institute of Technology Edwin Chong, Purdue University Sebastian Engell, University of Dortmund Toshio Fukuda, Nagoya University Zhiqiang Gao, Cleveland State University Dimitry Gorinevsky, Measurex Devron Inc. Ken Hunt, Daimler-Benz AG Tag Gon Kim, KAIST Mieczyslaw Kokar, Northeastern University Ken Loparo, Case Western Reserve University Kwang Lee, The Pennsylvania State University Michael Lemmon, University of Notre Dame Frank Lewis, University of Texas at Arlington Ping Liang, University of California, Riverside Derong Liu, General Motors R&D Center Kumpati Narendra, Yale University Anil Nerode, Cornell University Marios Polycarpou, University of Cincinnati S. Joe Qin, Fisher-Rosemount Systems, Inc. Tariq Samad, Honeywell Technology Center George Saridis, Rensselaer Polytechnic Institute Jennie Si, Arizona State University Mark Spong, University of Illinois at Urbana-Champaign Jeffrey Spooner, Sandia National Laboratories Harry Stephanou, Rensselaer Polytechnic Institute Kimon Valavanis, University of Southwestern Louisiana Li-Xin Wang, Hong Kong University of Science and Tech. Gary Yen, USAF Phillips Laboratory ************************************************************************** * Prof. Marios M. Polycarpou | TEL: (513) 556-4763 * * University of Cincinnati | FAX: (513) 556-7326 * * Dept. Electrical & Computer Engineering | * * Cincinnati, Ohio 45221-0030 | Email: polycarpou@uc.edu * ************************************************************************** From lbl@nagoya.bmc.riken.go.jp Thu Oct 26 16:33:55 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:52 -0500; AA17447 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:49 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ad16250; 26 Oct 95 0:33:23 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ad16248; 26 Oct 95 0:24:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14374; 26 Oct 95 0:23:48 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa19929; 25 Oct 95 22:16:45 EDT Received: from ns.bmc.riken.go.jp by RI.CMU.EDU id aa26216; 25 Oct 95 22:16:12 EDT Received: from xian (xian [134.160.96.17]) by nagoya.bmc.riken.go.jp (8.6.12+2.5Wb7/3.4Wbeta6-BMC-95061514) with SMTP id LAA22894; Thu, 26 Oct 1995 11:09:41 +0900 From: Bao-Liang Lu Received: by xian (5.x/3.4Wbeta6) id AA07409; Thu, 26 Oct 1995 11:15:42 +0900 Date: Thu, 26 Oct 1995 11:15:42 +0900 Message-Id: <9510260215.AA07409@xian> To: Connectionists@cs.cmu.edu Subject: Paper available: Transformation of NLP Problems Using Neural Nets Cc: lbl@nagoya.bmc.riken.go.jp X-Sun-Charset: US-ASCII The following paper, to appear in Annals of Mathematics and Artificial Intelligence, is available via anonymous FTP. (This work was presented at 1st Mathematics of Neural Networks and Applications (MANNA'95) Conference, 3-7 July 1995, Lady Margaret Hall, Oxford, UK) FTP-host:ftp.bmc.riken.go.jp FTP-file:pub/publish/Lu/lu-manna95.ps.Z ========================================================================== TITLE: Transformation of Nonlinear Programming Problems into Separable Ones Using Multilayer Neural Networks AUTHORS: Bao-Liang Lu (1) Koji Ito (1,2) ORGANISATIONS: (1) The Institute of Physical and Chemical Research (RIKEN) (2) Toyohashi University of Technology ABSTRACT: In this paper we present a novel method for transforming nonseparable nonlinear programming (NLP) problems into separable ones using multilayer neural networks. This method is based on a useful feature of multilayer neural networks, i.e., any nonseparable function can be approximately expressed as a separable one by a multilayer neural network. By use of this method, the nonseparable objective and (or) constraint functions in NLP problems can be approximated by multilayer neural networks, and therefore, any nonseparable NLP problem can be transformed into a separable one. The importance of this method lies in the fact that it provides us with a promising approach to using modified simplex methods to solve general NLP problems. (6 pages. No hard copies available.) Bao-Liang Lu --------------------------------------------- Bio-Mimetic Control Research Center, The Institute of Physical and Chemical Research (RIKEN) 3-8-31 Rokuban, Atsuta-ku, Nagoya 456, Japan Phone: +81-52-654-9137 Fax: +81-52-654-9138 Email: lbl@nagoya.bmc.riken.go.jp From mjo@cns.ed.ac.uk Thu Oct 26 16:33:56 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Thu, 26 Oct 95 16:33:49 -0500; AA17444 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Thu, 26 Oct 95 16:33:46 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ac16250; 26 Oct 95 0:32:24 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ac16248; 26 Oct 95 0:24:03 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14370; 26 Oct 95 0:23:46 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa04189; 20 Oct 95 11:50:14 EDT Received: from [129.215.144.9] by EDRC.CMU.EDU id aa13807; 20 Oct 95 11:46:26 EDT Received: (from mjo@localhost) by garbo.cns.ed.ac.uk (8.6.11/8.6.11) id QAA21458; Fri, 20 Oct 1995 16:45:16 +0100 Date: Fri, 20 Oct 1995 16:45:16 +0100 From: Mark Orr Message-Id: <199510201545.QAA21458@garbo.cns.ed.ac.uk> To: Connectionists@cs.cmu.edu Subject: Paper available: Local Smoothing of RBF Networks The following paper has been accepted for presentation at the International Symposium on Neural Networks, Hsinchu, Taiwan, December 1995. LOCAL SMOOTHING OF RADIAL BASIS FUNCTION NETWORKS Mark J.L. Orr Centre for Cognitive Science Edinburgh University Abstract: A method of supervised learning is described which enhances generalisation performance by adaptive local smoothing in the input space. The method exploits the local nature of radial basis functions and employs multiple smoothing parameters optimised by generalised cross-validation. More traditional approaches have only a single smoothing parameter and produce a globally uniform smoothing but are demonstrably less effective unless the target function itself is uniformly smooth. A postscript version of a slightly longer version (9 pages instead of 6) can be retrieved by following the links "publications" and "Neural Networks" from the world wide web page: http://www.cns.ed.ac.uk/people/mark.html Alternatively the paper can be retrieved by anonymous ftp: ftp://scott.cogsci.ed.ac.uk/pub/mjo/isann95-long.ps.Z Size: 77KB compressed, 155KB uncompressed. Sorry, no hardcopies. ---- Mark J L Orr, Centre for Cognitive Science, Edinburgh University, 2, Buccleuch Place, Edinburgh EH8 9LW, Scotland, UK phone: (+44) (0) 131 650 4413 email: mjo@cns.ed.ac.uk From S.Renals@dcs.shef.ac.uk Fri Oct 27 22:05:12 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 27 Oct 95 22:05:08 -0500; AA08274 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 27 Oct 95 22:05:06 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17576; 26 Oct 95 18:54:23 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17574; 26 Oct 95 18:32:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa15190; 26 Oct 95 18:31:32 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa29526; 26 Oct 95 11:11:00 EDT Received: from [143.167.8.2] by CS.CMU.EDU id aa14061; 26 Oct 95 11:09:49 EDT Received: from elvis.dcs.shef.ac.uk by dcs.shef.ac.uk (4.1/DAVE-1.0) id AA10253; Thu, 26 Oct 95 16:08:07 BST Received: by elvis.dcs.shef.ac.uk (8.6.9/SMI-4.1) id QAA12522; Thu, 26 Oct 1995 16:08:14 +0100 Date: Thu, 26 Oct 1995 16:08:14 +0100 From: S.Renals@dcs.shef.ac.uk Message-Id: <199510261508.QAA12522@elvis.dcs.shef.ac.uk> To: ml-connectionists@cs.cmu.edu, salt@cstr.ed.ac.uk, elsnet-list@let.ruu.nl, empiricists@csli.stanford.edu, ilash-members@dcs.shef.ac.uk Cc: s.renals@dcs.shef.ac.uk, ajr@eng.cam.ac.uk Subject: Research Positions in Speech Recognition As part of the EU funded project SPRACH (Speech Recognition Algorithms for Connectionist Hybrids) two Research Associate positions, of three years duration, are available at the Universities of Cambridge and Sheffield. Both positions are concerned with developing new methods for large vocabulary speech recognition. The Sheffield position will have an emphasis towards statistical language modelling; the Cambridge position will have an emphasis on connectionist acoustic models. The research project will build on the recently completed Wernicke project. One of the outcomes of that project is the Abbot large vocabulary speech recognition system, which is available in a demonstration version at ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/recognition/AbbotDemo/ The job adverts and application details are included below. For informal discussion contact either Steve Renals (s.renals@dcs.shef.ac.uk) or Tony Robinson (ajr@eng.cam.ac.uk). Tony Robinson, Cambridge University Steve Renals, Sheffield University ----------------------------------------------------------------------- University of Sheffield Department of Computer Science, Speech and Hearing Group Research Associate in Continuous Speech Recognition Applications are invited for a Research Associate to work in the speech and hearing group in the area of continuous speech recognition. In particular, the post will involve the investigation of new methods of statistical language modelling, approaches to domain adaptation and the development and evaluation of demonstration systems. The project is funded as a Basic Research Project by the EU and will be of three years duration, from December 1995. Candidates for the post will be expected to hold a postgraduate degree (preferably a PhD) in a relevant discipline, or to have acquired equivalent experience. The successful candidate will have had research experience in the area of statistical language modelling or connectionist/HMM-based speech recognition. Salary will be in the range \pounds 14,317 to \pounds 18,985. Informal enquiries about the post to Dr. Steve Renals (email: s.renals@dcs.shef.ac.uk; tel: +44-114-282-5575; fax: +44-114-278-0972). Further particulars and an application form are available from the Director of Human Resource Management, The University of Sheffield, Western Bank, Sheffield S10 2TN (tel: +44-114-282-4144; fax: +44-114-276-7897), citing Ref:R780. The closing date for applications is Friday 10 November 1995. The University of Sheffield follows an Equal Opportunity Policy. ----------------------------------------------------------------------- University of Cambridge Engineering Department, Speech Vision and Robotics group Research Associate in Large Vocabulary Connectionist Speech Recognition Applications are invited for a Research Assistantship in the use of connectionist models and hidden Markov models in large vocabulary automatic speech recognition. The project is funded by the EU and is of 36 months duration. Candidates for this post will have a good first degree and preferably a postgraduate degree in a relevant discipline. The candidate is expected to have prior knowledge of connectionist/Markov model hybrids, large vocabulary recognition or a related area. The ability to manage a large software project, participate in international evaluations and liaise with industry would be advantageous. Salary will be in the range \pounds 14,317 to \pounds 19,848. Further details and an application form may be obtained by writing to Dr Tony Robinson, Cambridge University Engineering Department, Trumpington Street, Cambridge CB2 1PZ, U.K., email ajr@eng.cam.ac.uk, phone +44-1223-332815, fax +44-1223-332662, or http://svr-www.eng.cam.ac.uk/~ajr. The deadline for applications is 26 November 1995. The University follows an equal opportunities policy. ----------------------------------------------------------------------- From listerrj@helios.aston.ac.uk Fri Oct 27 22:05:17 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 27 Oct 95 22:05:10 -0500; AA08276 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 27 Oct 95 22:05:08 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17610; 26 Oct 95 19:02:06 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17581; 26 Oct 95 18:35:22 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa15213; 26 Oct 95 18:34:37 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa03124; 26 Oct 95 14:06:28 EDT Received: from [134.151.79.46] by EDRC.CMU.EDU id aa11806; 26 Oct 95 14:03:45 EDT Received: from sun.aston.ac.uk (actually host dendrite.aston.ac.uk) by hermes.aston.ac.uk with SMTP (PP); Thu, 26 Oct 1995 18:08:05 +0000 Message-Id: <2120.9510261801@sun.aston.ac.uk> To: Connectionists@cs.cmu.edu Subject: Postdoctoral Research Fellowship Reply-To: listerrj@aston.ac.uk X-Mailer: Mew beta version 0.98 on Emacs 19.29.2 Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Date: Thu, 26 Oct 1995 19:01:12 +0100 From: Richard Lister Content-Length: 2074 ---------------------------------------------------------------------- Neural Computing Research Group ------------------------------- Dept of Computer Science and Applied Mathematics Aston University, Birmingham, UK POSTDOCTORAL RESEARCH FELLOWSHIP -------------------------------- Neural Networks for Visualisation of High-Dimensional Data ---------------------------------------------------------- *** Full details at http://neural-server.aston.ac.uk/ *** 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 novel techniques for data visualisation. The emphasis of the research will be on theoretically well-founded approaches which are applicable to real-world data sets. A key starting point for the research will be the recent developments in latent variable techniques for density estimation. Potential candidates should be have strong mathematical and computational skills, with a background either in artificial neural networks, statistical pattern recognition, or a related field. Conditions of Service --------------------- Salaries will be up to point 6 on the RA 1A scale, currently 15,986 UK pounds. The salary scale is subject to annual increments. How to Apply ------------ If you wish to be considered for this Fellowship, please send a full CV and publications list, including full details and grades of academic qualifications, together with the names of 4 referees, to: Professor C M Bishop Neural Computing Research Group Dept. of Computer Science and Applied Mathematics Aston University Birmingham B4 7ET, U.K. Tel: 0121 333 4631 Fax: 0121 333 6215 e-mail: c.m.bishop@aston.ac.uk (e-mail submission of postscript files is welcome) Closing date: 20 November, 1995. ---------------------------------------------------------------------- From eann96@lpac.ac.uk Fri Oct 27 22:05:18 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 27 Oct 95 22:05:14 -0500; AA08289 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 27 Oct 95 22:05:11 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19212; 27 Oct 95 14:15:23 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19209; 27 Oct 95 14:02:39 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa16087; 27 Oct 95 14:02:08 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa18940; 27 Oct 95 8:05:27 EDT Received: from gateway.lpac.ac.uk by EDRC.CMU.EDU id aa15855; 27 Oct 95 8:03:37 EDT Received: from pluto.lpac.ac.uk (pluto [138.37.76.61]) by gateway.lpac.ac.uk (8.6.12/8.6.12) with SMTP id KAA07717 for ; Fri, 27 Oct 1995 10:47:02 +0100 From: Engineering Apps in Neural Nets 96 Date: Fri, 27 Oct 95 09:46:22 GMT Message-Id: <20523.9510270946@pluto.lpac.ac.uk> To: connectionists@cs.cmu.edu Subject: EANN96-Second Call for Papers International Conference on Engineering Applications of Neural Networks (EANN '96) London, UK 17--19 June 1996 Second Call for Papers The conference is a forum for presenting the latest results on neural network applications in technical fields. The applications may be in any engineering or technical field, including but not limited to systems engineering, mechanical engineering, robotics, process engineering, metallurgy, pulp and paper technology, aeronautical engineering, computer science, machine vision, chemistry, chemical engineering, physics, electrical engineering, electronics, civil engineering, geophysical sciences, biotechnology, and environmental engineering. Abstracts of one page (200 to 400 words) should be sent to eann96@lpac.ac.uk by 21 January 1996 by e-mail in PostScript format or ASCII. Please mention two to four keywords, and whether you prefer it to be a short paper or a full paper. The short papers will be 4 pages in length, and full papers may be upto 8 pages. Tutorial proposals are also welcome until 21 January 1996. Notification of acceptance will be sent around 15 February. Submissions will be reviewed and the number of full papers will be very limited. For more information, please see the www page at http://www.lpac.ac.uk/EANN96 Organising committee A. Bulsari (Finland) D. Tsaptsinos (UK) T. Clarkson (UK) International program committee (to be confirmed, extended) G. Dorffner (Austria) S. Gong (UK) J. Heikkonen (Italy) B. Jervis (UK) E. Oja (Finland) H. Liljenstrvm (Sweden) G. Papadourakis (Greece) D. T. Pham (UK) P. Refenes (UK) N. Sharkey (UK) N. Steele (UK) D. Williams (UK) W. Duch (Poland) R. Baratti (Italy) G. Baier (Germany) E. Tulunay (Turkey) S. Kartalopoulos (USA) C. Schizas (Cyprus) J. Galvan (Spain) M. Ishikawa (Japan) Sponsored by: London Parallel Applications Centre (LPAC) IEE UK RIG NN British Institution of Electrical Engineers Professional Group C4 ---------------------------------+-------------------------------- Engineering Applications of Neural Networks'96 (EANN96) Further info: http://www.lpac.ac.uk/EANN96/ or Dimitris Tsaptsinos(D.Tsaptsinos@lpac.ac.uk) http://www.lpac.ac.uk/SEL-HPC/People/Dimitris ---------------------------------+-------------------------------- From gluck@pavlov.rutgers.edu Sat Oct 28 14:04:43 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 28 Oct 95 14:04:40 -0500; AA17176 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 28 Oct 95 14:04:37 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19517; 27 Oct 95 20:01:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19514; 27 Oct 95 19:44:44 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa16287; 27 Oct 95 19:44:31 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa27724; 27 Oct 95 17:05:24 EDT Received: from pavlov.rutgers.edu by CS.CMU.EDU id aa27892; 27 Oct 95 17:05:00 EDT Received: (from gluck@localhost) by pavlov.rutgers.edu (8.6.10+bestmx+oldruq+newsunq+grosshack/8.6.10) id RAA09224; Fri, 27 Oct 1995 17:30:01 -0400 Date: Fri, 27 Oct 1995 17:30:01 -0400 From: Mark Gluck Message-Id: <199510272130.RAA09224@pavlov.rutgers.edu> To: connectionists@cs.cmu.edu Subject: Graduate Training in NEURAL COMPUTATION at Rutgers Univ. (NJ), Behav. & Neural Sci Ph.D. Cc: gluck@pavlov.rutgers.edu Application Information for Ph.D. Program in BEHAVIORAL AND NEURAL SCIENCES at Rutgers University, Newark, New Jersey * Application target date is February 1, 1996 * ----------------------------------------------------------------- Additional information on our Ph.D. program, research facilities,and faculty can be obtained over the internet at: http://www.cmbn.rutgers.edu/bns-home.html ----------------------------------------------------------------- The Behavioral and Neural Sciences (BNS) graduate program at Rutgers-Newark aims to provide students with a rigorous understanding of modern neuroscience with an emphasis on integrating behavioral and neural approaches to understanding brain function. The program emphasizes the multidisciplinary nature of this endeavor, and offers specific research training in Behavioral and Cognitive Neuroscience as well as Molecular, Cellular and Systems Neuroscience. These research areas represent different but complementary approaches to contemporary issues in behavioral and molecular neuroscience and can emphasize either human or animal studies. The BNS graduate program is composed of faculty from the Center for Molecular and Behavioral Neuroscience (CMBN), the Institute of Animal Behavior (IAB), the Department of Biological Sciences, the Department of Psychology, and the School of Nursing. Research training in the BNS program emphasizes integration across levels of analysis and traditional disciplinary boundaries. Basic research areas in Cellular and Molecular Neuroscience include the study of the basal forebrain, basal ganglia, hippocampus, visual and auditory systems and monoaminergic and neuroendocrine systems using electrophysiological, neurochemical, neuroanatomical and molecular biological approaches. Research in Cognitive and Behavioral Neuroscience includes the study of memory, language (both signed and spoken), reading, attention, motor control, vision, and animal behavior. Clinically relevant research areas are the study of the behavioral, physiological and pharmacological aspects of schizophrenia, Alzheimer's Disease, amnesia, epilepsy, Parkinson's disease and other movement disorders, and the molecular genetics of neuropsychiatric disorders Other Information ----------------- At present the CMBN supports up to 40 students with 12-month renewable assistantships for a period of four years. The curent stipend for first year students is $12,750; this includes tuition remission and excellent healthcare benefits. In addition, the Johnson & Johnson pharmaceutical company's Foundation has provided four Excellence Awards which increase students' stipends by $5,000. Several other fellowships are offered. More information is available in our graduate brochure, available upon request. The Rutgers-Newark campus is 20 minutes outside New York City, and close to other major university research centers at NYU, Columbia, SUNY, and Princeton, as well as major industrial research labs in Northern NJ, including ATT, Bellcore, Siemens, and a host of pharmaceutical companies including Johnson & Johnson Hoecsht-Celanese, and Sandoz. Faculty Associated With Rutgers BNS Ph.D. Program ------------------------------------------------- FACULTY - RUTGERS Elizabeth Abercrombie (Ph.D., Princeton), neurotransmitters and behavior [CMBN] Colin Beer (Ph.D., Oxford), ethology [IAB] April Benasich (Ph.D., New York), infant perception and cognition [CMBN] Ed Bonder (Ph.D., Pennsylvania), cell biology [Biology] Linda Brzustowicz (M.D.,Ph.D., Columbia), human genetics [CMBN] Gyorgy Buzsaki (Ph.D., Budapest), systems neuroscience [CMBN] Mei-Fang Cheng (Ph.D., Bryn Mawr) neuroethology/neurobiology [IAB] Ian Creese (Ph.D., Cambridge), neuropsychopharmacology [CMBN] Doina Ganea (Ph.D., Illinois Medical School), molecular immunology [Biology] Alan Gilchrist (Ph.D., Rutgers), visual perception [Psychology] Mark Gluck (Ph.D.,Stanford), learning, memory and neural computation [CMBN] Ron Hart (Ph.D., Michigan), molecular neuroscience [Biology] G. Miller Jonakait (Ph.D., Cornell Medical College), neuroimmunology [Biology] Judy Kegl (Ph.D., M.I.T.), linguistics/neurolinguistics [CMBN] Barry Komisaruk (Ph.D., Rutgers), behavioral neurophysiology/pharmacology [IAB] Joan Morrell (Ph.D., Rochester), cellular neuroendocrinology [CMBN] Teresa Perney (Ph.D., Chicago), ion channel gene expression and function [CMBN] Howard Poizner (Ph.D., Northeastern), language and motor behavior [CMBN] Jay Rosenblatt (Ph.D., New York), maternal behavior [IAB] Anne Sereno (Ph.D., Harvard), attention and visual perception [CMBN] Maggie Shiffrar (Ph.D., Stanford), vision and motion perception[CMBN] Harold Siegel (Ph.D., Rutgers) neuroendocrine mechanisms [IAB] Ralph Siegel (Ph.D., McGill), neuropsychology of visual perception [CMBN] Jennifer Swann (Ph.D., Michigan), neuroendocrinology [Biology] Paula Tallal (Ph.D., Cambridge), neural basis of language development [CMBN] James Tepper (Ph.D., Colorado), basal ganglia neurophysiology and anatomy [CMBN] Beverly Whipple (Ph.D., Rutgers), women's health [Nursing] Laszlo Zaborszky (Ph.D., Hungarian Academy), neuroanatomy of forebrain [CMBN] ASSOCIATES OF CMBN Izrail Gelfand (Ph.D., Moscow State), biology of cells [Biology] Richard Katz (Ph.D., Bryn Mawr), psychopharmacology [Ciba Geigy] Barry Levin (M.D., Emory Medical) neurobiology David Tank (Ph.D., Cornell), neural plasticity [Bell Labs] For More Information or an Application -------------------------------------- If you are interested in applying to our graduate program, or possibly applying to one of the labs as a post-doc, research assistant or programmer, please contact us via one of the following: Dr. Gyorgy Buzsaki or Dr. Mark A. Gluck BNS Graduate Admissions CMBN, Rutgers University 197 University Ave. Newark, New Jersey 07102 Phone: (201) 648-1080 (Ext. 3221) Fax: (201) 648-1272 Email: buzsaki@axon.rutgers.edu or gluck@pavlov.rutgers.edu We will be happy to send you info on our research and graduate program, as well as set up an a possible visit to the Neuroscience Center here at Rutgers-Newark. Please also see our WWW Homepage listed above which contains extensive information on faculty research, degree requirements, local facilities, and more. From mm@santafe.edu Sat Oct 28 14:04:44 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 28 Oct 95 14:04:41 -0500; AA17178 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 28 Oct 95 14:04:39 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19536; 27 Oct 95 20:09:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19519; 27 Oct 95 19:45:35 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa16293; 27 Oct 95 19:44:43 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa28625; 27 Oct 95 17:47:28 EDT Received: from sfi.santafe.edu by CS.CMU.EDU id aa28212; 27 Oct 95 17:46:48 EDT Received: from shabikeschee (shabikeschee.santafe.edu) by sfi.santafe.edu (4.1/SMI-4.1) id AA25294; Fri, 27 Oct 95 15:44:46 MDT Date: Fri, 27 Oct 95 15:44:46 MDT Message-Id: <9510272144.AA25294@sfi.santafe.edu> Received: by shabikeschee (4.1/SMI-4.1) id AA11021; Fri, 27 Oct 95 15:44:45 MDT To: Connectionists@cs.cmu.edu From: Melanie Mitchell Subject: Postdoctoral fellowships at the Santa Fe Institute The Santa Fe Institute has an opening for one or more Postdoctoral Fellows beginning in September, 1996. The Institute's research program is devoted to the study of complex systems, especially complex adaptive systems. Systems and techniques currently under study include: the economy; the immune system; the brain; biomolecular sequence and structure; the origin of life; artificial life; models of evolution; adaptive computation and intelligent systems; complexity, entropy, and the physics of information; nonlinear modeling and prediction; the evolution of culture; the development of general-purpose simulation environments; and others. Postdoctoral Fellows work either on existing research projects or on projects of their own choosing. Candidates should have a Ph.D. (or expect to receive one before September 1996) and should have backgrounds in computer science, mathematics, economics, theoretical physics or chemistry, game theory, cognitive science, theoretical biology, dynamical systems theory, or related fields. A strong background in computational approaches is essential, as is an interest in interdisciplinary work. Evidence of this interest, in the form of previous research experience and publications, is important. Applicants should submit a curriculum vitae, list of publications, and statement of research interests, and arrange for three letters of recommendation. Incomplete applications will not be considered. All application materials must be received by February 15, 1996. Decisions will be made by April, 1996. Send applications to: Postdoctoral Committee, Santa Fe Institute, 1399 Hyde Park Road, Santa Fe, New Mexico 87501. Send complete application packages only, preferably hard copy, to the above address. Include your e-mail address and/or fax number. SFI is an equal opportunity employer. Women and minorities are encouraged to apply. More information about SFI and its research program can be found at SFI's web site: http://www.santafe.edu.