From RRoy@cim.cran.ac.uk Sun Jan 12 11:26:49 1997 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 LAA27006 for ; Sun, 12 Jan 1997 11:26:32 -0600 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id LAA19033 for ; Sun, 12 Jan 1997 11:26:27 -0600 (CST) Received: from (warabi.cs.uwa.oz.au [130.95.1.13]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id XAA24224; Sun, 12 Jan 1997 23:24:32 +0800 Message-Id: <199701121524.XAA24224@cs.uwa.oz.au> From: "Roy, Rajkumar" To: RRoy@cim.cran.ac.uk, AFEEMAIL@unl.edu, ai-stats@watstat.uwaterloo.ca, alife@cognet.ucla.edu, annrules@fit.qut.edu.au, arpanet-bboards@edu.mit.lcs.mc, bisc-group@diva.EECS.Berkeley.EDU, CADAM-L@listserv.syr.edu, cogpsy@neuro.psy.soton.ac.uk, colt@cs.uiuc.edu, connect-bb@ed.eusip, cti-econ@mailbase.ac.uk, design-list@arch.su.EDU.AU, ECDM@pdomain.uwindsor.ca, econometric-research@mailbase.ac.uk, elsnet-list@cogsci.edinburgh.ac.uk, epsynet%uhupvm1.BITNET@bitnet.mailgate.cs.mu.oz.au, fuzzy_food@mech.ubc.ca, genetic@dcs.sheffield.ac.uk, ilpnet@IJS.si, incon@dcs.sheffield.ac.uk, irl-net%irlearn.BITNET@bitnet.mailgate.cs.mu.oz.au, nl-kr@snyside.sunnyside.com, regli@cme.nist.gov, reinforce@cs.uwa.edu.au, trade@csf.colorado.edu Subject: WSC2: First Call for Papers ... Date: Fri, 10 Jan 97 16:15:10 First Call for Papers 2nd Online World Conference on Soft Computing in Engineering Design and Manufacturing (WSC2) 23-27 June 1997 On the Internet (World-Wide Web) Hosted by: The CIM Institute, Cranfield University, United Kingdom University of Bath, United Kingdom Indian Institute of Technology, Mumbai, India Michigan State University, East Lansing, USA --------------------------------------------------------------------------- WSC2 Servers: http://www.zen.co.uk/cim.inst/wsc2/ http://www.bath.ac.uk/Departments/Eng/wsc2/home.html http://www.iitb.ernet.in/~soy/iitb/144.16.105.2/wsc2/ http://isl.cps.msu.edu/GA/wsc2/ --------------------------------------------------------------------------- OVERVIEW: Original papers are invited for the 2nd Online World Conference on Soft Computing (WSC2) to be held on the Internet. WSC2 will bring together practitioners and researchers in soft computing in engineering design and manufacturing across the world with the aim to publish quality research rapidly and with less cost. Special features of WSC2 are: * Good Quality Original Papers * Invited Key Papers * Virtual Exhibition * Best Paper Prizes * FTP and Email facility for those without Web access * Possible publication of selected papers in a journal WSC2 is the premier online event on soft computing and its application to engineering design and manufacturing. The previous event, WSC1 hosted by Nagoya University, Japan in August 1996 can be visited at http://www.bioele.nuee.nagoya-u.ac.jp/wsc1 TOPICS OF INTEREST: The scope of this conference covers the following soft computing and related techniques and their application to engineering design and manufacturing: Neural Networks Genetic Algorithms Other Stochastic Optimisation Techniques Fuzzy Logic Hybrid Methods Intelligent Agents and Agent Theory Causal Models Data Mining Probabilistic Reasoning Case-based Reasoning Chaos Theory Interactive Computational Models The application areas of interest include but are not limited to : Decision Support Process and System Control System Identification and Modelling Optimisation Signal or Image Processing Vision or Pattern Recognition Condition Monitoring Fault Diagnosis Systems Integration Innovation Collaborative Work Internet Tools Conference tracks will cover the following THEMES: 1. General problem solving issues in different areas of engineering design and manufacturing and how Soft Computing can address those issues more effectively than the conventional techniques. 2. Successful industrial applications and case studies; application methodologies; Good Practice Guides on soft computing applications. 3. Soft computing architectures; practical models of soft computing; computational costs. 4. Prototypes and tools for soft computing; Internet-accessible tools; distributed soft agents. 5. Human-computer interaction (HCI), social and Legal issues (copyright, IPR), international standards. In addition to research papers, the conference also welcomes good surveys and tutorial-style papers. CONFERENCE SCHEDULE: Full Papers submission by: 1 April 1997 Decision on Full Papers: 1 May 1997 Revised Final Manuscripts due: 1 June 1997 WSC2 Preview Week: 16-22 June 1997 WSC2 Conference Week: 23-27 June 1997 Deadline for Booking Exhibition Stand: 15 April 1997 WSC2 Virtual Exhibition Opens: 1 May 1997 WSC2 Virtual Exhibition Closes: 1 August 1997 SUBMISSION PROCEDURE: Full papers should be sent by email directly to the Program Chair at P.K.Chawdhry@bath.ac.uk before their respective deadlines. Full Papers should be submitted in Postscript format; however authors are encouraged for an additional submission in HTML format. The maximum size for the full paper is 10 X A4 pages. Papers should be written in 10-points Times-Roman or a similar font, with 2.5cm margins on all four sides. Detailed instructions for authors are available from: http://www.zen.co.uk/cim.inst/wsc2/form/author.html. For the HTML files please include all relevant graphic and text files. All links should be made to local files. At the time of sending the final manuscript by email to the Program Chair, authors should also send the Copyright Form by postal mail or fax to the Conference Chair. The copyright form is available from: http://www.zen.co.uk/cim.inst/wsc2/form/copyright.html CONFERENCE PROCEEDINGS: Full papers will be reviewed by a panel of referees prior to their acceptance. Authors are expected to make all necessary changes as suggested by the reviewers before the final submission of full paper manuscript. The WSC2 post-conference proceedings including all accepted papers will be published both in an Online version and a Hardcopy version. Expanded version of selected papers will be considered for publication in a journal after the conference. OFFICIAL LANGUAGE: All papers and online discussion during the conference will be in English. Main texts in the HTML and Postscript files should only include International Latin-2 character set, and Greek symbols for mathematical expressions. CONFERENCE FORMAT: WSC2 will be held online on the World Wide Web. This means that there will be contents of both static and dynamic nature. Full contents will be accessible only to the registered participants. However there will be some information that will be accessible to everyone over the Internet without restriction. The conference will consist of two parts: Technical Sessions and a Virtual Exhibition. Technical Sessions will be based on contributed research papers and invited key papers. These will include full papers plus a rolling slide presentation and any discussion between the authors and the participants. * Full papers will be available online at the WSC2 Servers starting the Conference Preview week to all registered participants to read. Abstracts of the accepted papers will also be available from 15 May 1997 to everyone on the Internet without restriction. * Authors are encouraged to provide Rolling slide presentations during the Conference week. The presentations shall be hosted online by the authors' own hosts on the Internet. The presentations would also include any online demonstrations of results that the authors might wish to show. Links to these presentations will be made from the Technical Sessions page of the WSC2 Servers to ensure uniform access to the registered participants. * Discussion on the technical papers will be enabled during the Conference week and all questions and answers will be available as online threads on the WSC2 Servers during this period. Only registered participants will be able to take part in discussion. VIRTUAL EXHIBITION of commercial, industrial and academic stands will complement the technical programme of WSC2. It will present information on commercial products, industrial projects and academic research groups related to soft computing and engineering design & manufacturing. Companies and professional organisations interested in the development or use of soft computing will also be welcome to present their perspective. Virtual Exhibit Stands will aim to cover a broad spectrum of state-of-the-art products and projects that are of interest to the soft computing and engineering design & manufacturing community. The Virtual Exhibition will be accessible by anyone on the Internet without restriction in order to give maximum exposure to the exhibits. The Copyright of Virtual Exhibit Stands will remain with their original owners. The Virtual Exhibition will come live on WSC2 Servers on 1 May 1997 and will be available until 1 August 1997. Exhibit Stands can be booked in advance by returning the attached Booking Form . Further details are available from our WSC2 server. CONFERENCE SPONSORSHIP: WSC2 provides an excellent opportunity for Companies and Professional Institutions to influence future trends and promote leadership in soft computing, engineering design and manufacturing by way of sponsorship. Experience shows that online conferences are accessed extensively by professionals all over the world. The participants include academics, researchers and practitioners from the industry. Description about your organisation will be published live on the WSC2 Servers during an extended period of 3 months around the WSC2 conference, from 1 May 1997 to 1 August 1997. The description of Sponsor's Pages will be created and owned by the sponsors themselves. Expression of interest for sponsorship can be sent by returning the attached Sponsorship Form . Further details are available from our WSC2 server. AWARDS: The conference will recognise excellence of contributions in a number of ways and the following five awards will be made at the end of the conference: * Best Overall Paper Award: for overall originality, presentation, discussion and online demonstration of results. * Best Presentation Award: for the combined highest quality of the written paper, rolling presentation slides and discussion * Best Online Demonstration Award: for highest quality online (possibly interactive) demonstration of results * Best Industrial Stand Award: to the industrial stand that best combines interest, information and stimulation for the conference * Best Academic Stand Award: to the academic stand that best combines its own research information, online demonstrations, useful pointers to related Internet resources, and stimulation for the conference INTERNATIONAL ORGANISING COMMITTEE: Rajkumar Roy, Cranfield University (UK) - Conference Chair Takeshi Furuhashi, Nagoya University (Japan) - International Co-Chair Pravir Chawdhry, University of Bath (UK) - Program Chair R. K. Pant, Indian Institute of Technology, Mumbai (India) - Publication Chair Charles McManus, Cranfield University (UK) - Local Organisation Chair For SUBMISSION and progress of papers in technical sessions, please contact the Program Chair: Pravir Chawdhry School of Mechanical Engineering University of Bath Bath BA2 7AY, United Kingdom Tel +44 (0)1225 826956 Fax +44 (0)1225 826928 Email: P.K.Chawdhry@bath.ac.uk For FURTHER INFORMATION, registration, exhibition booking and sponsorship, please contact the Conference Chair: Rajkumar Roy WSC2 Virtual Conference Office (wsc2@cim.cranfield.ac.uk) The CIM Institute Cranfield University Cranfield, Bedford MK43 0AL United Kingdom Tel. +44 (0)1234 754073 Ext. 2860 Fax. +44 (0)1234 750852 Email: rroy@cim.cranfield.ac.uk or r.roy@ieee.org --------------------------------------------------------------------------- Paper Submission Form Paper Title : Authors : Affiliation : Address : Phone : Fax : E-mail : Home URL: Keywords : Slide presentation / Demonstration URL (due by 1 June 1997): Abstract: --------------------------------------------------------------------------- Conference Registration Form Register for WSC2 now free of charge: Name : Affiliation : Address : Phone : Fax : E-mail : Home URL: Topic(s) of Interest : Username you would like to use for accessing WSC2: Password: --------------------------------------------------------------------------- Virtual Exhibition Stand Booking Software Vendors, Industries and Research Groups: Book your Exhibit Stand for WSC2 now. No payment required for the expression of interest below: Product / Project / Stand Title: Contact Person: Organisation: Address: Phone: Fax: E-mail: Home URL: Keywords: Exhibit Stand's URL: --------------------------------------------------------------------------- Sponsorship Form Companies, Universities and Professional Institutions: Your Sponsorship for WSC2 is valuable to the conference. No payment required for the expression of interest below: Sponsorship Category: Contact Person: Organisation: Address: Phone: Fax: E-mail: Home URL: Keywords: Sponsorship Page URL: --------------------------------------------------------------------------- From giles@research.nj.nec.com Mon Jan 13 14:12:55 1997 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 OAA15618 for ; Mon, 13 Jan 1997 14:12:48 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id OAA03271 for ; Mon, 13 Jan 1997 14:12:39 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa22407; 13 Jan 97 11:45:10 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa22405; 13 Jan 97 11:10:49 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa21939; 13 Jan 97 11:10:10 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa04592; 13 Jan 97 10:39:51 EST Received: from zingo.nj.nec.com by RI.CMU.EDU id aa27185; 13 Jan 97 10:39:02 EST Received: from alta (alta [138.15.159.81]) by zingo.nj.nec.com (8.7.4/8.7.3) with SMTP id KAA05746 for ; Mon, 13 Jan 1997 10:38:44 -0500 (EST) Received: by alta (5.52/cliff's joyful mailer #2) id AA26649(alta); Mon, 13 Jan 97 10:36:48 EST Date: Mon, 13 Jan 97 10:36:48 EST From: Lee Giles Message-Id: <9701131536.AA26649@alta> To: connectionists@cs.cmu.edu Subject: TR available The following TR is available from the NEC Research Institute and University of Maryland UMIACS archives. _______________________________________________________________________ A Delay Damage Model Selection Algorithm for NARX Neural Networks Tsungnan Lin{1,2}, C. Lee Giles{1,3}, Bill G. Horne{1}, Sun-Yang Kung{2} {1} NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 {2} Dept. of Electrical Engineering, Princeton U., Princeton, NJ 08540 {3} UMIACS, University of Maryland, College Park, MD 20742 U. of Maryland Technical Report CS-TR-3707 and UMIACS-TR-96-77 ABSTRACT Recurrent neural networks have become popular models for system identification and time series prediction. NARX (Nonlinear AutoRegressive models with eXogenous inputs) neural network models are a popular subclass of recurrent networks and have beenused in many applications. Though embedded memory can be found in all recurrent network models, it is particularly prominent in NARX models. We show that using intelligent memory order selection through pruning and good initial heuristics significantly improves the generalization and predictive performance of these nonlinear systems on problems as diverse as grammatical inference and time series prediction. Keywords: Recurrent neural networks, tapped-delay lines, long-term dependencies, time series, automata, memory, temporal sequences, gradient descent training, latching, NARX networks, auto-regressive, pruning, embedding theory. _________________________________________________________________________ http://www.neci.nj.nec.com/homepages/giles.html http://www.cs.umd.edu/TRs/TR-no-abs.html -- C. Lee Giles / Computer Sciences / NEC Research Institute / 4 Independence Way / Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482 www.neci.nj.nec.com/homepages/giles.html == From lazzaro@CS.Berkeley.EDU Mon Jan 13 23:14:05 1997 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 XAA27175 for ; Mon, 13 Jan 1997 23:14:00 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id XAA10912 for ; Mon, 13 Jan 1997 23:13:59 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab22945; 13 Jan 97 21:20:40 EST Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab22943; 13 Jan 97 21:06:53 EST Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa14852; 13 Jan 97 21:06 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa15570; 13 Jan 97 19:14:00 EST Received: from snap.CS.Berkeley.EDU by EDRC.CMU.EDU id aa10107; 13 Jan 97 19:13:05 EST Received: (from lazzaro@localhost) by snap.CS.Berkeley.EDU (8.8.3/8.6.9) id QAA16004 for connectionists@cs.cmu.edu; Mon, 13 Jan 1997 16:13:02 -0800 (PST) Date: Mon, 13 Jan 1997 16:13:02 -0800 (PST) From: John Lazzaro Message-Id: <199701140013.QAA16004@snap.CS.Berkeley.EDU> To: connectionists@cs.cmu.edu Subject: New silicon audition papers online ... Two new papers on silicon audition available online ... --john lazzaro (presented at NIPS*96) A Micropower Analog VLSI HMM State Decoder for Wordspotting John Lazzaro and John Wawrzynek CS Division, UC Berkeley Richard Lippmann MIT Lincoln Laboratory ABSTRACT We describe the implementation of a hidden Markov model state decoding system, a component for a wordspotting speech recognition system. The key specification for this state decoder design is microwatt power dissipation; this requirement led to a continuous-time, analog circuit implementation. We describe the tradeoffs inherent in the choice of an analog design and explain the mapping of the discrete-time state decoding algorithm into the continuous domain. We characterize the operation of a 10-word (81 state) state decoder test chip. Available on the Web at: http://http.cs.berkeley.edu/~lazzaro/biblio/decoder.ps.gz (forthcoming UCB Technical Report) Anawake: Signal-Based Power Management For Digital Signal Processing Systems John Lazzaro and John Wawrzynek CS Division, UC Berkeley Richard Lippmann MIT Lincoln Laboratory ABSTRACT Single-chip, low-power, programmable digital signal processing systems are capable of hosting complete speech processing applications, while consuming a few milliwatts of average power. We present a power management architecture that decreases the average power consumption of these systems to 3--10 microwatts, in applications where speech signals are present with a sufficiently low duty cycle. In this architecture, a micropower analog signal processing system, {\it Anawake,} continuously analyzes the incoming signal, and controls the power consumption of the DSP system in a signal-dependent way. We estimate system power consumption for Anawake designs optimized for different peak-speech-signal to average-background-noise ratios. Available on the Web at: http://http.cs.berkeley.edu/~lazzaro/biblio/anawake.ps.gz From harmonme@aa.wpafb.af.mil Tue Jan 14 06:07:56 1997 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 GAA01201 for ; Tue, 14 Jan 1997 06:07:50 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id GAA14135 for ; Tue, 14 Jan 1997 06:07:49 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa22945; 13 Jan 97 21:19:21 EST Received: from SKINNER.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa22943; 13 Jan 97 21:06:51 EST Received: from skinner.boltz.cs.cmu.edu by skinner.boltz.cs.cmu.edu id aa14847; 13 Jan 97 21:06 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ad13955; 13 Jan 97 18:02:12 EST Received: from [134.131.12.18] by EDRC.CMU.EDU id aa08915; 13 Jan 97 16:05:53 EST Received: by ethel.aa.wpafb.af.mil; (5.65v3.2/1.1.8.2/18Jan94-0348PM) id AA14059; Mon, 13 Jan 1997 16:06:19 -0500 Alternate-Recipient: allowed Auto-Forwarded: prohibited Content-Return: allowed Disclose-Recipients: prohibited Conversion: allowed Importance: normal Priority: normal Sensitivity: Company-Confidential Subject: On-Line, Interactive RL Tutorial From: "Mance E. Harmon" To: connectionists@cs.cmu.edu Message-Id: <970113160614.648@ethel.aa.wpafb.af.mil.0> Date: Mon, 13 Jan 97 16:06:16 -0500 X-Mailer: MailWorks 2.0-1 Reinforcement Learning: An On-Line, Interactive Tutorial by Mance E. Harmon http://eureka1.aa.wpafb.af.mil/rltutorial (hardcopy length: 19 Pages) Scope of Tutorial The purpose of this tutorial is to provide an introduction to reinforcement learning (RL) at a level easily understood by students and researchers in a wide range of disciplines. The intent is not to present a rigorous mathematical discussion that requires a great deal of effort on the part of the reader, but rather to present a conceptual framework that might serve as an introduction to a more rigorous study of RL. The fundamental principles and techniques used to solve RL problems are presented. The most popular RL algorithms are presented and interactively demonstrated using WebSim, a Java-based simulation development environment. Section 1 presents an overview of RL and provides a simple example to develop intuition of the underlying dynamic programming mechanism. In Section 2 the parts of a reinforcement learning problem are discussed. These include the environment, reinforcement function, and value function. Section 3 gives a description of the most widely used reinforcement learning algorithms. These include TD(lambda) and both the residual and direct forms of value iteration, Q-learning, and advantage learning. In Section 4 some of the ancillary issues in RL are briefly discussed, such as choosing an exploration strategy and an appropriate discount factor. The conclusion is given in Section 5. Finally, Section 6 is a glossary of commonly used terms followed by references in Section 7 and a bibliography of RL applications in Section 8. It is assumed that the reader has some knowledge of learning algorithms that rely on gradient descent (such as the backpropagation of errors algorithm). Mance Harmon harmonme@aa.wpafb.af.mil From movellan@ergo.ucsd.edu Tue Jan 14 20:35:37 1997 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 UAA16112 for ; Tue, 14 Jan 1997 20:35:33 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id UAA26375 for ; Tue, 14 Jan 1997 20:35:31 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00894; 14 Jan 97 20:43:11 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00892; 14 Jan 97 20:24:37 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23469; 14 Jan 97 20:24:21 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa06064; 14 Jan 97 15:25:27 EST Received: from ergo.ucsd.edu by CS.CMU.EDU id aa13745; 14 Jan 97 15:23:33 EST Received: (from movellan@localhost) by ergo.ucsd.edu (8.7.6/8.7.3) id MAA00743; Tue, 14 Jan 1997 12:15:13 -0800 Date: Tue, 14 Jan 1997 12:15:13 -0800 Message-Id: <199701142015.MAA00743@ergo.ucsd.edu> From: "Javier R. Movellan" To: Connectionists@cs.cmu.edu Subject: UCSD Cogsci Tech Report 97.01 UCSD.Cogsci.TR.97.01 AUTHORS: Javier R. Movellan and Paul Mineiro TITLE: Modularity and Catastrophic Fusion: A Bayesian Approach with Applications to Audiovisual Speech Recognition. ABSTRACT: While modular architectures have desirable properties, integrating the outputs of many modules into a unified representation is not a trivial issue. In this paper we examine catastrophic fusion, a problem that occurs when modules are fused in incorrect context conditions. This problem has become especially apparent in the current research on automatic recognition of multimodal signals and has practical as well as theoretical relevance. Catastrophic fusion arises because modules make implicit assumptions and thus operate correctly only within a certain context. Practice shows that when modules are tested in contexts inconsistent with their assumptions, their influence on the fused product tends to increase, with catastrophic results. We propose a principled solution to this problem based upon Bayesian ideas of competitive models. We study the approach analytically on a classic Gaussian discrimination task and then apply it to a realistic problem on audiovisual speech recognition (AVSR) with excellent results. For concreteness our emphasis is on applications to AVSR but the problems at hand are very general and touch fundamental issues about cognitive architectures. ELECTRONIC COPIES: http://cogsci.ucsd.edu and follow the link to "Tech Reports" PHYSICAL COPIES: Available for $7.00 within the US, $10.00 outside the US. For physical copies send a check of money order payable to UC Regents and mail it to the following address, TR Request Javier R. Movellan Department of Cognitive Science University of California San Diego La Jolla, Ca 92093-0515 From marks@u.washington.edu Wed Jan 15 05:34:17 1997 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 FAA22821 for ; Wed, 15 Jan 1997 05:34:10 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id FAA00455 for ; Wed, 15 Jan 1997 05:34:09 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab00975; 14 Jan 97 20:53:49 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab00896; 14 Jan 97 20:25:29 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23480; 14 Jan 97 20:24:46 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa10769; 14 Jan 97 18:47:42 EST Received: from carson.u.washington.edu by EDRC.CMU.EDU id aa17274; 14 Jan 97 18:46:17 EST Received: by carson.u.washington.edu (5.65+UW96.08/UW-NDC Revision: 2.33 ) id AA20188; Tue, 14 Jan 97 15:45:23 -0800 Date: Tue, 14 Jan 97 15:45:23 -0800 From: Robert Marks Message-Id: <9701142345.AA20188@carson.u.washington.edu> X-Sender: marks@carson.u.washington.edu To: Connectionists@cs.cmu.edu Subject: IEEE TNN now on-line Cc: marks@ee.washington.edu The IEEE Transactions on Neural Networks is now on line. It is currently free to IEEE members. The web address is: http://www.opera.ieee.org/jolly/ Have your IEEE number handy. IEEE membership information is available on the NNC home page. http://engine.ieee.org/nnc/ Robert J. Marks II, Editor-in-Chief IEEE Transactions on Neural Networks r.marks@ieee.org From gjr@cra.com Wed Jan 15 05:34:18 1997 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 FAA22819 for ; Wed, 15 Jan 1997 05:34:09 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id FAA00449 for ; Wed, 15 Jan 1997 05:34:08 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00975; 14 Jan 97 20:53:12 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00896; 14 Jan 97 20:25:28 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa23474; 14 Jan 97 20:24:35 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa08257; 14 Jan 97 16:58:55 EST Received: from [205.181.6.150] by EDRC.CMU.EDU id aa16520; 14 Jan 97 16:57:43 EST Received: from [205.181.6.162] by mail.cra.com with SMTP (Apple Internet Mail Server 1.1.1); Tue, 14 Jan 1997 17:05:31 -0400 X-Sender: gjr@mail.cra.com Message-Id: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Date: Tue, 14 Jan 1997 17:04:52 -0500 To: Connectionists@cs.cmu.edu From: Gerard J Rinkus Subject: Thesis available: Neural model integrating episodic, semantic and temporal sequence memory FTP-host: cns-ftp.bu.edu FTP-filename: /pub/rinkus/thesis_*.Z The following Ph.D. Thesis is available via either anonymous ftp or my web site (no hardcopies available). It is 249 pages long and the chapters can be retrieved individually. (Specific retrieval instructions below). =========================================================== Title: A Combinatorial Neural Network Exhibiting Episodic and Semantic Memory Properties for Spatio-Temporal Patterns Gerard J. Rinkus Dept. of Cognitive and Neural Systems Boston University Boston, MA 02215 rinkus@cns.bu.edu http://cns-web.bu.edu/pub/rinkus/www/ ABSTRACT This thesis describes TEMECOR (Temporal Episodic MEmory using COmbinatorial Representations), an unsupervised, distributed, associative network model of storage, retrieval and recognition of binary spatio-temporal patterns, exhibiting episodic, semantic and complex sequence memory. The original version of the model, TEMECOR-I, meets several essential requirements of episodic memory-very high capacity, single-trial learning, permanence (stability) of traces, and the ability to store highly-overlapped spatio-temporal patterns, including complex state sequences (CSSs) which are sequences in which the same state can recur multiple times-e.g., [A B B A G C B A D]. Various parametric simulation studies are reported, revealing that the model's capacity increases faster-than-linearly in the size (i.e., number of nodes) of the network, for both uncorrelated and correlated (specifically, complex sequence) spatio-temporal pattern sets. However, TEMECOR-I fails to possess the crucial property that similar inputs map to similar internal representations-i.e., continuity. Therefore the model fails to exhibit similarity-based generalization and categorization, which are the basis of many of those phenomena classed as semantic memory. A second version of the model, TEMECOR-II, adds the property of continuity and therefore constitutes a single associative neural network which exhibits both episodic and semantic memory properties, and which does so for the spatio-temporal pattern domain. TEMECOR-II achieves the continuity property by computing, on each time slice, t, the degree of match, G(t), between its expected and actual inputs and then adding an amount of noise, inversely proportional to G(t), into the process of choosing a final internal representation at t. This generally leads to reactivation of old traces (i.e., greater pattern completion) in proportion to the familiarity of inputs, and establishment of new traces (i.e., greater pattern separation) in proportion to the novelty of inputs. Simulation results are given for TEMECOR-II, demonstrating the embedding of similarity relationships in the model's adaptive mappings between inputs and internal representations, and the model's ability to co-categorize similar spatio-temporal events. The model is monolithic in that all three types of memory are explained by a single local circuit architecture, instantiating a winner-take-all network, that is proposed as an analog of the cortical minicolumn. Thus, episodic (i.e., exemplar-specific) and semantic (i.e., general, category-level) information coexist in the same physical substrate. A principle/mechanism is described whereby the model's instantaneous level of memory access-along the spectrum between highly specific (based on the details of a single exemplar) and highly generic (based on the general properties of a class of exemplars) memory access-can be controlled by modulation of various threshold parameters. =========================================================== FTP instructions: (e.g. to retrieve chapter 1) unix> ftp cns-ftp.bu.edu Name: anonymous Password: your full email address ftp> cd pub/rinkus ftp> get thesis_chap1.ps.Z ftp> bye unix> uncompress thesis_chap1.ps.Z ..then send to a postscript printer or previewer Note: the file names and page lengths are: thesis_chap1.ps.Z ch. 1 49 (incl. prelim pages) thesis_chap2.ps.Z ch. 2 24 thesis_chap3.ps.Z ch. 3 29 thesis_chap4.ps.Z ch. 4 113 thesis_chap5.ps.Z ch. 5 5 thesis_refs.ps.Z refs. 11 From moody@chianti.cse.ogi.edu Wed Jan 15 15:52:18 1997 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 PAA02217 for ; Wed, 15 Jan 1997 15:52:13 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id PAA08370 for ; Wed, 15 Jan 1997 15:52:09 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02558; 15 Jan 97 12:59:58 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02556; 15 Jan 97 12:38:40 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa24373; 15 Jan 97 12:38:21 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa19334; 15 Jan 97 1:54:45 EST Received: from cse.ogi.edu by RI.CMU.EDU id aa10184; 15 Jan 97 1:54:19 EST Received: from chianti.cse.ogi.edu by church.cse.ogi.edu with smtp (Smail3.1.29.1 #5) id m0vkPEm-000049C; Tue, 14 Jan 97 22:54 PST Received: by chianti.cse.ogi.edu (NX5.67e/NX3.0S) id AA10106; Tue, 14 Jan 97 22:54:15 -0800 Date: Tue, 14 Jan 97 22:54:15 -0800 From: John Moody Message-Id: <9701150654.AA10106@chianti.cse.ogi.edu> To: connectionists@cs.cmu.edu Subject: Research Position in Statistical Learning Cc: moody@chianti.cse.ogi.edu, sherid@chianti.cse.ogi.edu Research Position in Nonparametric Statistics, Neural Networks and Machine Learning at Department of Computer Science & Engineering Oregon Graduate Institute of Science & Technology I am seeking a highly qualified researcher to take a leading role on a project involving the development and testing of new model selection and input variable subset selection algorithms for classification, regression, and time series prediction applications. Candidates should have a PhD in Statistics, EE, CS, or a related field, have experience in neural network modeling, nonparametric statistics or machine learning, have strong C programming skills, and preferably have experience with S-Plus and Matlab. The compensation and level of appointment (Postdoctoral Research Associate or Senior Research Associate) will depend upon experience. The initial appointment will be for one year, but may be extended depending upon the availability of funding. Candidates who can start by April 1, 1997 or before will be given preference, although an extremely qualified candidate who is available by June 1 may also be considered. If you are interested in applying for this position, please mail, fax, or email your CV (ascii text or postscript only), a letter of application, and a list of at least three references (names, addresses, emails, phone numbers) to: Ms. Sheri Dhuyvetter Computer Science & Engineering Oregon Graduate Institute PO Box 91000 Portland, OR 97291-1000 Phone: (503) 690-1476 FAX: (503) 690-1548 Email: sherid@cse.ogi.edu Please do not send applications to me directly. I will consider all applications received by Sheri on or before January 31. OGI (Oregon Graduate Institute of Science and Technology) has over a dozen faculty, senior research staff, and postdocs doing research in Neural Networks, Machine Learning, Signal Processing, Time Series, Control, Speech, Language, Vision, and Computational Finance. Short descriptions of our research interests are appended below. Additional information is available on the Web at http://www.cse.ogi.edu/Neural/ and http://www.cse.ogi.edu/CompFin/ . OGI is a young, but rapidly growing, private research institute located in the Silicon Forest area west of downtown Portland, Oregon. OGI offers Masters and PhD programs in Computer Science and Engineering, Electrical Engineering, Applied Physics, Materials Science and Engineering, Environmental Science and Engineering, Chemistry, Biochemistry, Molecular Biology, Management, and Computational Finance. The Portland area has a high concentration of high tech companies that includes major firms like Intel, Hewlett Packard, Tektronix, Sequent Computer, Mentor Graphics, Wacker Siltronics, and numerous smaller companies like Planar Systems, FLIR Systems, Flight Dynamics, and Adaptive Solutions (an OGI spin-off that manufactures high performance parallel computers for neural network and signal processing applications). +++++++++++++++++++++++++++++++++++++++++++++++++++++++ Oregon Graduate Institute of Science & Technology Department of Computer Science & Engineering Department of Electrical Engineering Research Interests of Faculty, Research Staff, and Postdocs in Neural Networks, Machine Learning, Signal Processing, Control, Speech, Language, Vision, Time Series, and Computational Finance Etienne Barnard (Associate Professor, EE): Etienne Barnard is interested in the theory, design and implementation of pattern-recognition systems, classifiers, and neural networks. He is also interested in adaptive control systems -- specifically, the design of near-optimal controllers for real- world problems such as robotics. Ron Cole (Professor, CSE): Ron Cole is director of the Center for Spoken Language Understanding at OGI. Research in the Center currently focuses on speaker- independent recognition of continuous speech over the telephone and automatic language identification for English and ten other languages. The approach combines knowledge of hearing, speech perception, acoustic phonetics, prosody and linguistics with neural networks to produce systems that work in the real world. Mark Fanty (Research Assistant Professor, CSE): Mark Fanty's research interests include continuous speech recognition for the telephone; natural language and dialog for spoken language systems; neural networks for speech recognition; and voice control of computers. Dan Hammerstrom (Associate Professor, CSE): Based on research performed at the Institute, Dan Hammerstrom and several of his students have spun out a company, Adaptive Solutions Inc., which is creating massively parallel computer hardware for the acceleration of neural network and pattern recognition applications. There are close ties between OGI and Adaptive Solutions. Dan is still on the faculty of the Oregon Graduate Institute and continues to study next generation VLSI neurocomputer architectures. Hynek Hermansky (Associate Professor, EE); Hynek Hermansky is interested in speech processing by humans and machines with engineering applications in speech and speaker recognition, speech coding, enhancement, and synthesis. His main research interest is in practical engineering models of human information processing. Todd K. Leen (Associate Professor, CSE): Todd Leen's research spans theory of neural network models, architecture and algorithm design and applications to speech recognition. His theoretical work is currently focused on the foundations of stochastic learning, while his work on Algorithm design is focused on fast algorithms for non-linear data modeling. John Moody (Associate Professor, CSE): John Moody does research on the design and analysis of learning algorithms, statistical learning theory (including generalization and model selection), optimization methods (both deterministic and stochastic), and applications to signal processing, time series, economics, and computational finance. David Novick (Associate Professor, CSE): David Novick conducts research in interactive systems, including computational models of conversation, technologically mediated communication, and human-computer interaction. A central theme of this research is the role of meta-acts in the control of interaction. Current projects include dialogue models for telephone-based information systems. Misha Pavel (Associate Professor, EE): Misha Pavel does mathematical and neural modeling of adaptive behaviors including visual processing, pattern recognition, visually guided motor control, categorization, and decision making. He is also interested in the application of these models to sensor fusion, visually guided vehicular control, and human-computer interfaces. Hong Pi (Senior Research Associate, CSE) Hong Pi's research interests include neural network models, time series analysis, and dynamical systems theory. He currently works on the applications of nonlinear modeling and analysis techniques to time series prediction problems and financial market analysis. Pieter Vermeulen (Senior Research Associate, CSE): Pieter Vermeulen is interested in the theory, design and implementation of pattern-recognition systems, neural networks and telephone based speech systems. He currently works on the realization of speaker independent, small vocabulary interfaces to the public telephone network. Current projects include voice dialing, a system to collect the year 2000 census information and the rapid prototyping of such systems. Eric A. Wan (Assistant Professor, EE): Eric Wan's research interests include learning algorithms and architectures for neural networks and adaptive signal processing. He is particularly interested in neural applications to time series prediction, adaptive control, active noise cancellation, and telecommunications. Lizhong Wu (Senior Research Associate, CSE): Lizhong Wu's research interests include neural network theory and modeling, time series analysis and prediction, pattern classification and recognition, signal processing, vector quantization, source coding and data compression. He is now working on the application of neural networks and nonparametric statistical paradigms to finance. From lemmon@endeavor.ee.nd.edu Wed Jan 15 15:52:21 1997 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 PAA02221 for ; Wed, 15 Jan 1997 15:52:17 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id PAA08374 for ; Wed, 15 Jan 1997 15:52:13 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab02558; 15 Jan 97 13:00:58 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab02556; 15 Jan 97 12:38:42 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa24378; 15 Jan 97 12:38:33 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa26540; 15 Jan 97 9:19:35 EST Received: from nd.edu by EDRC.CMU.EDU id aa21045; 15 Jan 97 9:18:43 EST Received: from endeavor.ee.nd.edu by nd.edu with ND-SMTP (PP); Wed, 15 Jan 1997 09:16:09 -0500 Received: by endeavor.ee.nd.edu (8.6.10/1.34) id JAA00690; Wed, 15 Jan 1997 09:16:07 -0500 Date: Wed, 15 Jan 1997 09:16:07 -0500 From: Michael Lemmon Message-Id: <199701151416.JAA00690@endeavor.ee.nd.edu> To: Connectionists@cs.cmu.edu Subject: IEEE-TAC Special Issue Contributed by Michael D. Lemmon (lemmon@maddog.ee.nd.edu) FIRST CALL FOR PAPERS IEEE Transactions on Automatic Control announces a Special Issue on ARTIFICIAL NEURAL NETWORKS IN CONTROL, IDENTIFICATION, and DECISION MAKING Edited by Anthony N. Michel Michael Lemmon Dept of Electrical Engineering Dept. of Electrical Engineering University of Notre Dame University of Notre Dame Notre Dame, IN 46556, USA Notre Dame, IN, 46556, USA (219)-631-5534 (voice) (219)-631-8309 (voice) (219)-631-4393 (fax) (219)-631-4393 (fax) Anthony.N.Michel.1@nd.edu lemmon@maddog.ee.nd.edu There is a growing body of experimental work suggesting that artificial neural networks can be very adept at solving pattern classification problems where there is significant real-world uncertainty. Neural networks also provide an analog method for quickly determining approximate solutions to complex optimization problems. Both of these capabilities can be of great use in solving various control problems and in recent years there has been increased interest in the use of artificial neural networks in the control and supervision of complex dynamical systems. This announcement is a call for papers addressing the topic of neural networks in control, identification, and decision making. Accepted papers will be published in a special issue of the IEEE Transactions of Automatic Control. The special issue is seeking papers which use formal analysis to establish the role of neural networks in control, identification, and decision making. For this reason, papers consisting primarily of empirical simulation results will not be considered for publication. Before submitting, prospective authors should consult past issues of the IEEE Transactions on Automatic Control to identify the type of results and the level of mathematical rigor that are the norm in this journal. Submitted papers are due by July 1, 1997 and should be sent to Michael D. Lemmon or Anthony N. Michel. Notification of acceptance decisions will be sent by December 31, 1997. The special issue is targeted for publication in 1998 or early 1999. All papers will be refereed in accordance with IEEE guidelines. Please consult the inside back cover of any recent issue of the Transactions on Automatic Control for style and length of the manuscript and the number of required copies (seven copies with cover letter) to be sent to one of the editors of this special issue. From marwan@ee.usyd.edu.au Thu Jan 16 14:31:33 1997 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 OAA15659 for ; Thu, 16 Jan 1997 14:31:28 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id OAA23426 for ; Thu, 16 Jan 1997 14:31:20 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa04181; 16 Jan 97 12:30:45 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa04179; 16 Jan 97 12:06:21 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa25614; 16 Jan 97 12:05:43 EST Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa19175; 16 Jan 97 5:05:26 EST Received: from [129.78.24.47] by EDRC.CMU.EDU id aa27979; 16 Jan 97 5:04:37 EST Received: from sedal (sedal.sedal.usyd.EDU.AU [129.78.24.47]) by sedal.sedal.su.oz.au (8.6.9/8.6.9) with SMTP id VAA10647 for ; Thu, 16 Jan 1997 21:03:50 +1100 Date: Thu, 16 Jan 1997 21:03:49 +1100 (EST) From: Marwan Jabri X-Sender: marwan@sedal To: Connectionists Subject: Postgraduate scholarship Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Postgraduate scholarship Models and implementations of spiking networks This is a scholarship funded by the Australian Research Council for a period of three years to fund a student styding towards a PhD. Students applying for this scholarship should have a first class Honors or equivalent in electrical/computer engineering. The scholarship amounts to A$18,000 per year. The area of investigation is the development of models, learning algorithms and associated VLSI implementations of spiking networks. Note that non-Australian residents have to pay fees to enrol at Australian universities. The amount of fees can be consulted by looking the University of Sydney web page (www.usyd.edu.au). Applicants should forward to my address below a CV including copies of scripts of academic record and the names, email, phone, fax, and addresses of two academic referees. Deadline is Friday Feb 7, 1997. ------------ Marwan Jabri Professor in Adaptive Systems Dept of Electrical Engineering, The University of Sydney NSW 2006, Australia Tel: (+61-2) 9351-2240, Fax: (+61-2) 9351-7209, Mobile: (+61) 414-512240 Email: marwan@sedal.usyd.edu.au, http://www.sedal.usyd.edu.au/~marwan/ From mesegal@aehn2.einstein.edu Fri Jan 17 18:37:38 1997 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 SAA09724 for ; Fri, 17 Jan 1997 18:37:31 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id SAA15000 for ; Fri, 17 Jan 1997 18:37:30 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05661; 17 Jan 97 17:46:00 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05641; 17 Jan 97 17:10:07 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa26904; 17 Jan 97 17:09:51 EST Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa21228; 16 Jan 97 9:27:16 EST Received: from aehn2.einstein.edu by CS.CMU.EDU id aa02339; 16 Jan 97 9:26:58 EST Received: from novix (ipservice.einstein.edu [205.245.102.1]) by aehn2.einstein.edu (8.6.12/8.6.9) with SMTP id JAA25147; Thu, 16 Jan 1997 09:24:36 GMT Date: Thu, 16 Jan 1997 09:24:36 GMT Message-Id: <199701160924.JAA25147@aehn2.einstein.edu> X-Sender: mesegal@aehn2.einstein.edu (Unverified) X-Mailer: Windows Eudora Light Version 1.5.2 Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: neuron@CATTELL.psych.upenn.edu, connectionists@cs.cmu.edu, biomedical-sig-inns@msc.anl.gov From: mary segal Subject: Recruitment for fellows in neural networks/rehabilitation research FELLOWSHIPS AVAILABLE IN NEURAL NETWORKS RELATED TO COGNITIVE NEUROSCIENCE AND REHABILITATION RESEARCH The Moss Rehabilitation Research Institute (MRRI) is accepting applications for two-year research fellowships. MRRI provides an opportunity for mutual collaboration with senior investigators in the field; educational conferences, lab meetings, and weekly patient rounds; and access to a variety of patient populations. Requirements include a PhD in a relevant area of cognitive neuroscience or rehabilitation, training in research design, and applied experience in data collection and analysis. Projects are funded through Federal agencies, such as the National Institutes of Health, as well as private foundations. Individuals with the following interests are invited to apply for the 1997-1998 fellowships: Applications of neural networks to both theoretical and applied problems in rehabilitation research, including 1) cognitive processing and/or acquired language disorders, e.g. in stroke patients; 2) relationship between areas of muscle weakness and compensatory musculoskeletal overuse symptoms in polio and other neurologic diseases; and/or 3) prediction of functional outcomes in rehabilitation patients. Mentors include Drs. John Whyte, MRRI director; Myrna Schwartz, MRRI associate director; Laurel Buxbaum; Branch Coslett; Mary Klein; Susan Kohn; and Mary Segal. MRRI is affiliated with a number of area academic institutions and has close ties with departments of physical medicine and rehabilitation, psychology, cognitive neuroscience, neurology, and bioengineering at various institutions including the University of Pennsylvania, Temple University, Lehigh University, and Drexel University. MRRI is an equal opportunity employer. For more information contact Mary Segal, Moss Rehabilitation Research Institute, MossRehab Hospital, 213 Korman Building, 1200 West Tabor Road, Philadelphia, PA 19141; telephone (215) 456-9901 ext. 9181; FAX (215) 456-9514; e-mail mesegal@aehn2.einstein.edu. From anderson@magnum.cog.brown.edu Fri Jan 17 22:10:29 1997 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 WAA11705 for ; Fri, 17 Jan 1997 22:10:23 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id WAA17083 for ; Fri, 17 Jan 1997 22:10:21 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05639; 17 Jan 97 17:36:04 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05637; 17 Jan 97 17:09:08 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa26897; 17 Jan 97 17:08:57 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa14582; 17 Jan 97 9:41:27 EST Received: from magnum.cog.brown.edu by RI.CMU.EDU id aa28278; 17 Jan 97 9:39:03 EST Received: by magnum.cog.brown.edu (MX V4.1 VAX) id 11; Fri, 17 Jan 1997 09:30:59 EST Date: Fri, 17 Jan 1997 09:30:58 EST From: anderson@magnum.cog.brown.edu To: connectionists@cs.cmu.edu Message-ID: <009AE7E1.9C226A40.11@magnum.cog.brown.edu> Subject: Faculty Position in Cognition, Brown University FACULTY POSITION IN COGNITION, BROWN UNIVERSITY. The Department of Cognitive and Linguistic Sciences at Brown University invites applications for a four-year faculty position in Human Cognition, to begin July 1, 1997 (initial three year appointment with one year renewal, non-tenure-track). The position would be suited to either a senior visitor who would receive half-time salary support and teach two courses per year, or a more junior applicant who would receive full salary support and teach three courses per year. Candidates should have core teaching and research interests in an area of human cognition such as perception, attention, memory, categorization, problem solving, reasoning, or decision making, as well as an interest in interacting with members of an interdisciplinary department. Familiarity with computational modeling is desirable. All applicants must have received the Ph.D. degree or equivalent by the beginning of the appointment. The initial deadline for applications is March 1, 1997, but applications will be accepted after that time until the position is filled. Please send CV, recent publications, and a cover letter describing teaching and research interests to the address below. Senior applicants should enclose the names of three referees; junior applicants should have three letters of reference sent to: Cognitive Search Committee, Department of Cognitive and Linguistic Sciences, Box 1978, Brown University, Providence, RI 02912. Brown is an Equal Opportunity/Affirmative Action employer. Women and minorities are especially encouraged to apply. From bruno@redwood.ucdavis.edu Sat Jan 18 04:27:53 1997 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 EAA15060 for ; Sat, 18 Jan 1997 04:27:48 -0600 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.7.6/8.7.3) with SMTP id EAA19753 for ; Sat, 18 Jan 1997 04:27:46 -0600 (CST) Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa06011; 17 Jan 97 22:35:44 EST Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa06009; 17 Jan 97 22:27:23 EST Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa27267; 17 Jan 97 22:26:41 EST Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa28132; 17 Jan 97 21:05:34 EST Received: from redwood.ucdavis.edu by RI.CMU.EDU id aa02914; 17 Jan 97 21:04:30 EST Received: by redwood.ucdavis.edu (940816.SGI.8.6.9/940406.SGI.AUTO) id SAA20962; Fri, 17 Jan 1997 18:05:41 -0800 Date: Fri, 17 Jan 1997 18:05:41 -0800 From: "Bruno A. Olshausen" Message-Id: <199701180205.SAA20962@redwood.ucdavis.edu> To: connectionists@cs.cmu.edu Subject: grad program, UC Davis GRADUATE PROGRAM IN NEUROSCIENCE UNIVERSITY OF CALIFORNIA, DAVIS The Graduate Program in Neuroscience at the University of California, Davis offers interdisciplinary training in areas from molecular to cognitive neuroscience. Many research opportunities exist for students interested in computational modeling approaches to problems in neuroscience. The Center for Neuroscience and the Institute for Theoretical Dynamics provide students and faculty with numerous research facilities and an excellent environment for combining theoretical and experimental approaches. Relevant faculty include: David Amaral - structure and function of hippocampus, amygdala Ken Britten - visual cortex, neural basis of motion perception Leo Chalupa - retina neurophysiology, development Barbara Chapman - development and plasticity of sensory systems Charles Gray - cortical mechanisms of pattern recognition, rhythmic activity Andrew Ishida - retinal ganglion cells, synaptic integration Joel Keizer - computational modeling, cell physiology, calcium dynamics Leah Krubitzer - cortical organization, comparative anatomy Ron Mangun - selective attention, cognitive neuroimaging Bruno Olshausen - computational models of vision, efficient coding Robert Rafal - neuropsychology of visual attention Gregg Recanzone - cortical mechanisms of attention, sensory processing Lynn Robertson - spatial vision, object recognition, hemispheric differences Karen Sigvart - neural control of locomotion Mitch Sutter - cortical mechanisms of auditory perception, plasticity Martin Wilson - synaptic transmission in the retina *** Application deadline for fall admissions is February 15, 1997. *** Application materials may be obtained from: Ms. Dawne Shell tel: (916) 752-9091 or 9092 Graduate Group Complex fax: (916) 752-8822 188 Briggs Hall e-mail: drshell@ucdavis.edu University of California, Davis Davis, California 95616-8599 Specific questions regarding the program should be directed to: Lynn Roberston, Program Chair or David Amaral, Chair of Admissions (916) 757-8853 (916) 757-8813 (510) 372-2000 X6891 dgamaral@ucdavis.edu marva4!lynn@ucdavis.edu Web site: http://neuroscience.ucdavis.edu/ngg/