neuron-request@HPLABS.HP.COM ("Neuron-Digest Moderator Peter Marvit") (02/01/89)
Neuron Digest Monday, 30 Jan 1989 Volume 5 : Issue 6 Today's Topics: Administrivia Tech Report Announcement Connectionist Concepts: BBS Call for Commentators ICSI talk - Two Decades of Applied Kolmogorov Complexity Stanford Adaptive Networks Colloquium ICSI talk - Structured Representations CALL FOR PARTICIPATION ICSI talk - Efficient associative storage Call for papers for IJCNN Send submissions, questions, address maintenance and requests for old issues to "neuron-request@hplabs.hp.com" or "{any backbone,uunet}!hplabs!neuron-request" ARPANET users can get old issues via ftp from hplpm.hpl.hp.com (15.255.16.205). ------------------------------------------------------------ Subject: Administrivia From: "Your local Moderator" <neuron-request@hplabs.hp.com> Date: Mon, 31 Jan 89 20:00:00 -0800 [[This issue is devoted to talk announcements, calls for participation and so on. Astute readers will note that some of the dates are rather old. I've been experiencing some local mailer difficulties, plus the usual hectic schedule at the beginning of a new semester, which combined to delay. At this rate, I may never catch up! As usual, I include talk announcements, even though they are past, since they let readers know who's doing what in the field. For those of you who have requested back issues by mail... you haven't been forgotten. I appreciate your patience. For those who access back issues via ftp... please do it in the extreme off hours or on Mon/Wed/Fri mornings; you are accessing my personal workstation and ftp gets pretty low priority when I'm doing something else. Finally, if you are missing issues, please let me know. Vol4 ended (arbitrarily) at #34. -Peter Marvit ]] ------------------------------ Subject: Tech Report Announcement From: eric@mcc.com (Eric Hartman) Date: Mon, 02 Jan 89 16:02:06 -0600 The following MCC Technical Report is now available. Requests may be sent to eric@mcc.com or Eric Hartman Microelectronics and Computer Technology Corporation 3500 West Balcones Center Drive Austin, TX 78759-6509 U.S.A. ----------------------------------------------------------------- Explorations of the Mean Field Theory Learning Algorithm Carsten Peterson* and Eric Hartman Microelectronics and Computer Technology Corporation 3500 West Balcones Center Drive Austin, TX 78759-6509 MCC Technical Report Number: ACA-ST/HI-065-88 Abstract: The mean field theory (MFT) learning algorithm is elaborated and explored with respect to a variety of tasks. MFT is benchmarked against the back propagation learning algorithm (BP) on two different feature recognition problems: two-dimensional mirror symmetry and eight-dimensional statistical pattern classification. We find that while the two algorithms are very similar with respect to generalization properties, MFT normally requires a substantially smaller number of training epochs than BP. Since the MFT model is bidirectional, rather than feed-forward, its use can be extended naturally from purely functional mappings to a content addressable memory. A network with N visible and N hidden units can store up to approximately 2N patterns with good content-addressability. We stress an implementational advantage for MFT: it is natural for VLSI circuitry. Also, its inherent parallelism can be exploited with fully synchronous updating, allowing efficient simulations on SIMD architectures. *Present Address: Department of Theoretical Physics University of Lund Solvegatan 14A, S-22362 Lund, Sweden ------------------------------ Subject: Connectionist Concepts: BBS Call for Commentators From: harnad@Princeton.EDU (Stevan Harnad) Date: Wed, 04 Jan 89 10:12:06 -0500 Below is the abstract of a forthcoming target article to appear in Behavioral and Brain Sciences (BBS), an international, interdisciplinary journal that provides Open Peer Commentary on important and controversial current research in the biobehavioral and cognitive sciences. Commentators must be current BBS Associates or nominated by a current BBS Associate. To be considered as a commentator on this article, to suggest other appropriate commentators, or for information about how to become a BBS Associate, please send email to: harnad@confidence.princeton.edu or write to: BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771] ____________________________________________________________________ THE CONNECTIONIST CONSTRUCTION OF CONCEPTS Adrian Cussins, New College, Oxford Keywords: connectionism, representation, cognition, perception, nonconceptual content, concepts, learning, objectivity, semantics Computational modelling of cognition depends on an underlying theory of representation. Classical cognitive science has exploited the syntax/semantics theory of representation derived from formal logic. As a consequence, the kind of psychological explanation supported by classical cognitive science is "conceptualist": psychological phenomena are modelled in terms of relations between concepts and between the sensors/effectors and concepts. This kind of explanation is inappropriate according to Smolensky's "Proper Treatment of Connectionism" [BBS 11(1) 1988]. Is there an alternative theory of representation that retains the advantages of classical theory but does not force psychological explanation into the conceptualist mold? I outline such an alternative by introducing an experience-based notion of nonconceptual content and by showing how a complex construction out of nonconceptual content can satisfy classical constraints on cognition. Cognitive structure is not interconceptual but intraconceptual. The theory of representational structure within concepts allows psychological phenomena to be explained as the progressive emergence of objectivity. This can be modelled computationally by transformations of nonconceptual content which progressively decrease its perspective-dependence through the formation of a cognitive map. Stevan Harnad ARPA/INTERNET harnad@confidence.princeton.edu harnad@princeton.edu harnad@mind.princeton.edu srh@flash.bellcore.com harnad@elbereth.rutgers.edu CSNET: harnad%mind.princeton.edu@relay.cs.net UUCP: harnad@princeton.uucp BITNET: harnad@pucc.bitnet harnad1@umass.bitnet Phone: (609)-921-7771 ------------------------------ Subject: ICSI talk - Two Decades of Applied Kolmogorov Complexity From: baker%icsi.Berkeley.EDU@berkeley.edu (Paula Ann Baker) Date: Wed, 04 Jan 89 15:37:43 -0800 The International Computer Science Institute is pleased to present a talk: Friday, January 13, 1989 2:00 p.m. Paul M.B. Vitanyi Centrum voor Wiskunde en Informatica, Amsterdam and Department of Mathematics and Computer Science University of Amsterdam "Two Decades of Applied Kolmogorov Complexity" This talk is an introduction to the main ideas of Kolmogorov complexity and surveys the wealth of useful applications of this elegant notion. Topics include notions of randomness; a version of Goedel's incompleteness theorem; lower bound arguments in formal language theory, complexity of computation, and electronic chips; Bayesian inference and a priori probability with applications ranging from foundational issues to the theory of learning and inductive inference in Artificial Intelligence; resource-bounded Kolmogorov complexity with applications ranging from NP-completeness and the P versus NP question to cryptography. (We will treat these subjects as far and in such multitude as feasible.) This is joint work with Ming Li, and is a selection from the textbook ``An Introduction to Kolmogorov Complexity and its Applications'' we are preparing. This talk will be held in the Main Lecture Hall at ICSI. 1947 Center Street, Suite 600, Berkeley, CA 94704 (On Center between Milvia and Martin Luther King Jr. Way) ------------------------------ Subject: Stanford Adaptive Networks Colloquium From: netlist@psych.Stanford.EDU (Mark Gluck) Date: Tue, 10 Jan 89 06:43:16 -0800 Stanford University Interdisciplinary Colloquium Series: ADAPTIVE NETWORKS AND THEIR APPLICATIONS Co-sponsored by the Departments of Psychology and Electrical Engineering Winter Quarter 1989 Schedule ---------------------------- Jan. 12th (Thursday, 3:30pm): ----------------------------- STEVEN PINKER CONNECTIONISM AND Department of Brain & Cognitive Sciences THE FACTS OF HUMAN LANGUAGE Massachusetts Institute of Technology email: steve@psyche.mit.edu (with commentary by David Rumelhart) Jan. 24th (Tuesday, 3:30pm): ---------------------------- LARRY MALONEY LEARNING BY ASSERTION: Department of Psychology CALIBRATING A SIMPLE VISUAL SYSTEM New York University email: ltm@xp.psych.nyu.edu Feb. 9th (Thursday, 3:30pm): ---------------------------- CARVER MEAD VLSI MODELS OF NEURAL NETWORKS Moore Professor of Computer Science California Institute of Technology Feb. 21st (Tuesday, 3:30pm): ---------------------------- PIERRE BALDI ON SPACE AND TIME IN NEURAL COMPUTATIONS Jet Propulsion Laboratory California Institute of Technology email: pfbaldi@caltech.bitnet Mar. 14th (Tuesday, 3:30pm): ---------------------------- ALAN LAPEDES NONLINEAR SIGNAL PROCESSING WITH NEURAL NETS Theoretical Division - MS B213 Los Alamos National Laboratory email: asl@lanl.gov Additional Information ---------------------- The talks (including discussion) last about one hour and fifteen minutes. Following each talk, there will be a reception. Unless otherwise noted, all talks will be held in room 380-380F, which is in the basement of the Mathematical Sciences buildings. To be placed on an electronic-mail distribution list for information about these and other adaptive network events in the Stanford area, send email to netlist@psych.stanford.edu. For additional information, contact: Mark Gluck, Department of Psychology, Bldg. 420, Stanford University, Stanford, CA 94305 (phone 415-725-2434 or email to gluck@psych.stanford.edu). Program Committe: Committee: Bernard Widrow (E.E.), David Rumelhart, Misha Pavel, Mark Gluck (Psychology). This series is supported by the Departments of Psychology and Electrical Engineering and by a gift from the Thomson-CSF Corporation. Coming this Spring: D. Parker, B. McNaughton, G. Lynch & R. Granger ------------------------------ Subject: ICSI talk - Structured Representations From: baker%icsi.Berkeley.EDU@berkeley.edu (Paula Ann Baker) Date: Wed, 11 Jan 89 16:10:45 -0800 The International Computer Science Institute is pleased to present a talk: Wednesday, January 18, 1989 12:00 p.m. "Structured representations and connectionist models" Jeff Elman Departments of Cognitive Science and Linguistics University of California, San Diego Recent descriptions of connectionist models have argued that connectionist representations are unstructured, atomic, and bounded (e.g., Fodor & Pylyshyn, 1988). I will describe several sets of results with recurrent networks and distri- buted representations which contest these claims. The simu- lations address the type/token distinction, the representa- tion of hierarchical categories in language, and the representation of grammatical structure; the results suggest that connectionist networks are able to learn representa- tions which are indeed richly structured and open-ended. I will also discuss the notion that trajectories through state space provide a useful representational dimension which is available to connectionist models. A method is presented for analyzing the dynamic aspects of the represen- tations which arise in recurrent networks. The method involves rotating the dimensions of the hidden unit space in order to extract meaningful dimensions and constructing phase state portraits of projections of the hidden unit time series along selected dimensions. These phase state por- traits are then analyzed in terms of linguistic (grammati- cal) structure. This talk will be held in the Main Lecture Hall at ICSI. 1947 Center Street, Suite 600, Berkeley, CA 94704 (On Center between Milvia and Martin Luther King Jr. Way) ------------------------------ Subject: CALL FOR PARTICIPATION From: "Joerg Kindermann" <unido!gmdzi!joerg@uunet.UU.NET> Date: Thu, 12 Jan 89 08:30:50 -0100 Workshop ``DANIP'' Distributed Adaptive Neural Information Processing. 24.-25.4.1989 Gesellschaft fuer Mathematik und Datenverarbeitung mbH Sankt Augustin Neural information processing is constantly gaining increasing attention in many scientific areas. As a consequence the first ``Workshop Konnektionismus'' at the GMD was organized in February 1988. It gave an overview of research activities in neural networks and their applications to Artificial Intelligence. Now, almost a year later, the time has come to focus on the state of neural information processing itself. The aim of the workshop is to discuss TECHNICAL aspects of information processing in neural networks on the basis of personal contributions in one of the following areas: - new or improved learning algorithms (including evaluations) - self organization of structured (non-localist) neural networks - time series analysis by means of neural networks - adaptivity, e.g the problem of relearning - adequate coding of information for neural processing - generalization - weight interpretation (correlative and other)} Presentations which report on ``work in progress'' are encouraged. The size of the workshop will be limited to 15 contributions of 30 minutes in length. A limited number of additional participants may attend the workshop and take part in the discussions. To apply for the workshop as a contributor, please send information about your contribution (1-2 pages in English or a relevant publication). If you want to participate without giving an oral presentation, please include a description of your background in the field of neural networks. Proceedings on the basis of workshop contributions will be published after the workshop. SCHEDULE: 28 February 1989: deadline for submission of applications 20 March 1989: notification of acceptance 24 - 25 April 1989: workshop ``DANIP'' 31 July 1989: deadline for submission of full papers to be included in the proceedings Applications should be sent to the following address: Dr. Joerg Kindermann or Alexander Linden Gesellschaft fuer Mathematik und Datenverarbeitung mbH - Schloss Birlinghoven - Postfach 1240 D-5205 Sankt Augustin 1 WEST GERMANY e-mail: joerg@gmdzi al@gmdzi ------------------------------ Subject: ICSI talk - Efficient associative storage From: baker%icsi.Berkeley.EDU@BERKELEY.EDU (Paula Ann Baker) Date: Thu, 12 Jan 89 17:19:04 -0800 The International Computer Science Institute is pleased to present a talk: Thursday, January 19th, 1989 2:00 p.m. Joachim Buhmann University of Southern California "Efficient associative storage of static patterns and pattern sequences." Low activity neural networks are proposed for efficient storage and recall of static patterns and pattern sequences. One of the most promising extensions of the concept of associative memories is storage of sequences of patterns. The neural network proposed stores a set of sparse coded patterns and the transitions between subsequent patterns. Transition times are controlled by the level of noise in the system which provides an universal mechanism to control the recall speed. Patterns are stored in the network by a sparse coding scheme, i.e. only few neurons are firing and most of the neurons are quiet. This coding scheme turns out to yield a much higher storage capacity than storage of random patterns as in the popular Hopfield model. By introducing global inhibition in the network all spurious states can be suppressed. This talk will be held in the Main Lecture Hall at ICSI. 1947 Center Street, Suite 600, Berkeley, CA 94704 (On Center between Milvia and Martin Luther King Jr. Way) ------------------------------ Subject: Call for papers for IJCNN From: pwh@ece-csc.ncsu.edu (Paul Hollis) Date: Fri, 13 Jan 89 17:28:39 -0500 [[Editor's note: PLEASE NOTE IMMEDIATE DATE FOR SUBMISSION! -PM]] NEURAL NETWORKS CALL FOR PAPERS International Joint Conference on Neural Networks June 18-22, 1989 Washington, D.C. The 1989 IEEE/INNS International Joint Conference on Neural Networks (IJCNN-89) will be held at the Sheraton Washington Hotel in Washington, D.C., USA from June 18-22, 1989. IJCNN-89 is the first conference in a new series devoted to the technology and science of neurocomputing and neural networks in all of their aspects. The series replaces the previous IEEE ICNN and INNS Annual Meeting series and is jointly sponsored by the IEEE Technical Activities Board Neural Network Committee and the International Neural Network Society (INNS). IJCNN-89 will be the only major neural net- work meeting of 1989 (IEEE ICNN-89 and the 1989 INNS Annual Meeting have both been cancelled). Thus, it behooves all members of the neural network community who have important new results for presentation to prepare their papers now and submit them by the IJCNN-89 deadline of 1 FEBRUARY 1989. The Conference Proceedings will be distributed AT THE REGISTRATION DESK to all regular conference registrants as well as to all student registrants. The conference will include a day of tutorials (June 18), the exhibit hall (the neurocomputing industry's primary annual trade show), plenary talks, and social events. Mark your calendar today and plan to attend IJCNN-89 -- the definitive annual progress report on the neurocomputing revolution! DEADLINE FOR SUBMISSION OF PAPERS for IJCNN-89 is FEBRUARY 1, 1989. Papers of 8 pages or less are solicited in the following areas: - -Real World Applications -Associative Memory - -Supervised Learning Theory -Image Analysis - -Reinforcement Learning Theory -Self-Organization - -Robotics and Control -Neurobiological Models - -Optical Neurocomputers -Vision - -Optimization -Electronic Neurocomputers - -Neural Network Architectures & Theory -Speech Recognition FULL PAPERS in camera-ready form (1 original on Author's Kit forms and 5 reduced 8 1/2" x 11" copies) should be submitted to Nomi Feldman, Confer- ence Coordinator, at the address below. For more details, or to request your IEEE Author's Kit, call or write: Nomi Feldman, IJCNN-89 Conference Coordinator 3770 Tansy Street, San Diego, CA 92121 (619) 453-6222 ------------------------------ End of Neurons Digest *********************