From munro@lis.pitt.edu Sun Jul 16 10:07:25 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sun, 16 Jul 95 10:07:23 -0500; AA27742 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sun, 16 Jul 95 10:07:21 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa09269; 16 Jul 95 8:07:19 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa09265; 16 Jul 95 7:57:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07429; 16 Jul 95 7:56:51 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa25750; 16 Jul 95 0:08:25 EDT Received: from icarus.lis.pitt.edu by CS.CMU.EDU id aa13765; 16 Jul 95 0:07:44 EDT Received: by icarus.lis.pitt.edu (4.1/1.34) id AA28789; Sun, 16 Jul 95 00:08:07 EDT Date: Sun, 16 Jul 1995 00:08:07 -0400 (EDT) From: Paul Munro Subject: Re: "Orthogonality" of the generalizers being combined To: Connectionists@cs.cmu.edu In-Reply-To: <9507020002.AA25348@sfi.santafe.edu> Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII On Sat, 1 Jul 1995, David Wolpert wrote: > > In his recent posting, Nathan Intrator writes > > >>> > combining, or in the simple case > averaging estimators is effective only if these estimators are made > somehow to be independent. > >>> > > This is an extremely important point. Its importance extends beyond (stuff deleted) > In other words, although those generalizers are about as different > from one another as can be, *as far as the data set in question was > concerned*, they were practically identical. This is a great flag that > one is in a data-limited scenario. I.e., if very different > generalizers perform identically, that's a good sign that you're > screwed. > > Which is a round-about way of saying that the independence Nathan > refers to is always with respect to the data set at hand. This is > discussed in a bit of detail in the papers referenced below. > > *** > > Getting back to the precise subject of Nathan's posting: Those > interested in a formal analysis touching on how the generalizers being > combined should differ from one another should read the Ander Krough > paper (to come out in NIPS7) that I mentioned in my previous > posting. A more intuitive discussion of this issue occurs in my > original paper on stacking, where there's a whole page of text > elaborating on the fact that "one wants the generalizers being > combined to (loosely speaking) 'span the space' of algorithms and be > 'mutually orthogonal'" to as much a degree as possible. (more stuff deleted) Bambang Parmanto and I have found that negative correlation among the individual classifiers can improve committee performance even more than zero correlation. So rather than a zero inner product (othogonality), a negative inner product is preferable. Of course, this may be just a matter of definition -- our comparisons are made using the error vector on a test set. That is, it's better for errors to be independent than it is for them to be coincident, but it's even better if the coincidence is below the expected coincidence rate for independent classifiers. Note that to ahieve a significant level of negative correlation, the overall generalization performance must be fairly high... From koiran@ICSI.Berkeley.EDU Sun Jul 16 23:42:32 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sun, 16 Jul 95 23:42:26 -0500; AA02335 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sun, 16 Jul 95 23:42:23 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10102; 16 Jul 95 22:40:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10100; 16 Jul 95 22:30:02 EDT Received: by DST.BOLTZ.CS.CMU.EDU id aa07963; 16 Jul 95 22:29:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa07958; 16 Jul 95 22:28:32 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa05693; 16 Jul 95 22:13:32 EDT Received: from icsia.ICSI.Berkeley.EDU by RI.CMU.EDU id aa03444; 16 Jul 95 22:13:06 EDT Received: from spare.ICSI.Berkeley.EDU (9964@spare.ICSI.Berkeley.EDU [128.32.201.54]) by icsia.ICSI.Berkeley.EDU (8.6.12/HUB+V8$Revision: 1.23 $) with ESMTP id TAA14059; Sun, 16 Jul 1995 19:12:56 -0700 From: Pascal Koiran Received: (koiran@localhost) by spare.ICSI.Berkeley.EDU (8.6.12/1.8) id TAA04679; Sun, 16 Jul 1995 19:12:52 -0700 Date: Sun, 16 Jul 1995 19:12:52 -0700 Message-Id: <199507170212.TAA04679@spare.ICSI.Berkeley.EDU> To: Connectionists@cs.cmu.edu Subject: Re: "Orthogonality" of the generalizers being combined Cc: koiran@ICSI.Berkeley.EDU Regarding this whole thread on "combinining generalizers", I am surprised that no one has ever mentioned the extensive work on "expert advice" in computational learning theory. Is this is simply by ignorance, or is there a more subtle reason ? As suggested by the list moderators, here are the names of a few people who have done relevant work : Cesa-bianchi, Freund, Haussler, Helmbold, Kivinen, Littlestone, Schapire. The seminal paper in the expert advice / on-line learning line of research seems to be: N. Littlestone (1988) Learning quickly when irrevelant attributes abound: a new linear-threshold algorithm. Machine Learning 2, 285-318. I am by no means an expert (no pun intended) in this area, so if you feel that your name was unfairly ommited from this list, I beg your forgiveness. Pascal Koiran. From mccallum@cs.rochester.edu Mon Jul 17 07:17:46 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 17 Jul 95 07:17:42 -0500; AA05957 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Mon, 17 Jul 95 07:17:34 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id NAA08489; Mon, 17 Jul 1995 13:40:42 +0800 Message-Id: <199507170540.NAA08489@cs.uwa.oz.au> From: Andrew McCallum To: malcolmr@cse.unsw.edu.au (Malcolm Ross Kinsella Ryan) Cc: reinforce@cs.uwa.edu.au (reinforcement mailing list) Subject: Re: Input Generalisation using decision trees Date: Sat, 15 Jul 1995 21:20:07 -0400 From: malcolmr@cse.unsw.edu.au (Malcolm Ross Kinsella Ryan) Date: Fri, 14 Jul 1995 12:45:28 +1000 (EST) I am interested in find out more about any work that has been done on generalising reinforcement information over large or continuous state spaces using decision trees. The only reference I have managed to find so far is Chapman and Kaelbling's "Input Generalisation in Delayed RL: An Algorithm and Performance Comp." You may find McCallum, R. Andrew "Instance-Based Utile Distinctions for Reinforcement Learning with Hidden State" Machine Learning Conference 1995 to be related also. The current version is designed to solve problems with "too little perception", (i.e. hidden state), rather than "too much perception" (many, many bits, or continuous many-D spaces), but the approach has significant similarities. I have work in progress that adapts this algorithm to find both *perceptual* and memory distinctions. \begin{abstract} We present {\it Utile Suffix Memory}, a reinforcement learning algorithm that uses short-term memory to overcome the state aliasing that results from hidden state. By combining the advantages of previous work in instance-based (or ``memory-based'') learning and previous work with statistical tests for separating noise from task structure, the method learns quickly, creates only as much memory as needed for the task at hand, and handles noise well. Utile Suffix Memory uses a tree-structured representation, and is related to work on Prediction Suffix Trees \cite{Ron94COLT}, Parti-game \cite{Moore94NIPS}, G-algorithm \cite{ChapmanKaelbling91}, and Variable Resolution Dynamic Programming \cite{Moore91ML}. \end{abstract} From georgiou@wiley.csusb.edu Mon Jul 17 17:10:58 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 17 Jul 95 17:10:54 -0500; AA10240 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Mon, 17 Jul 95 17:10:51 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11265; 17 Jul 95 14:43:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11263; 17 Jul 95 14:28:34 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08669; 17 Jul 95 14:26:59 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id ab18198; 17 Jul 95 14:05:03 EDT Received: from wiley.csusb.edu by RI.CMU.EDU id aa06221; 17 Jul 95 14:03:48 EDT Received: by wiley.csusb.edu (5.67a/1.34) id AA12508; Mon, 17 Jul 1995 11:07:35 -0700 Date: Mon, 17 Jul 1995 11:07:35 -0700 Message-Id: <199507171807.AA12508@wiley.csusb.edu> From: georgiou@wiley.csusb.edu To: Connectionists@cs.cmu.edu Subject: LFP: First Int'l Conf. on Computational Intelligence and Neurosciences Return-Receipt-To: georgiou@wiley.csusb.edu Please note the July 24, 1995, deadline. Papers are also accepted in TeX/LaTeX or postscript via email. For the full text of the call for papers please see: ftp://www.csci.csusb.edu/georgiou/ICCIN-95 and also ftp://www.csci.csusb.edu/georgiou/JCIS-95 ----------------------------------------------------------------------- Last Call for Papers FIRST INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCES September 28 to October 1, 1995. ``Shell Island'' Hotels of Wrightsville Beach, North Carolina, USA. Plenary Speakers include: James Anderson (Brown University) Subhash Kak (Louisiana State University) Haluk Ogmen (Houston of Houston) Ed Page (University of South Carolina) Jeffrey Sutton (Harvard University) L.E.H. Trainor (University of Toronto) Gregory H. Wakefield (University of Michigan) Summary Deadline: July 24, 1995 Decision & Notification: August 5, 1995 Send summaries to: George M. Georgiou Computer Science Department California State University San Bernardino, CA 92407 georgiou@wiley.csusb.edu Papers will be accepted based on summaries. A summary shall not exceed 4 pages of 10-point font, double-column, single-spaced text, (1 page minimum) with figures and tables included. From R.Poli@cs.bham.ac.uk Mon Jul 17 17:11:01 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 17 Jul 95 17:10:56 -0500; AA10242 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Mon, 17 Jul 95 17:10:53 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11277; 17 Jul 95 14:52:30 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11269; 17 Jul 95 14:31:50 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08675; 17 Jul 95 14:27:42 EDT Received: from MAILBOX.SRV.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa18693; 17 Jul 95 14:24:21 EDT Received: from percy.cs.bham.ac.uk by MAILBOX.SRV.CS.CMU.EDU id aa26671; 17 Jul 95 14:10:09 EDT Received: from sonic by percy.cs.bham.ac.uk with SMTP (PP) id <02646-0@percy.cs.bham.ac.uk>; Mon, 17 Jul 1995 18:28:24 +0100 Received: by sonic.cs.bham.ac.uk (4.1/client/1.2) id AA07327; Mon, 17 Jul 95 18:28:44 BST Date: Mon, 17 Jul 95 18:28:44 BST From: R.Poli@cs.bham.ac.uk Message-Id: <7327.9507171728@sonic.cs.bham.ac.uk> To: colt@cs.uiuc.edu, connectionists@MAILBOX.SRV.CS.CMU.EDU, evolutionary-computing@mailbase.ac.uk, ga-molecule-approval@INTERVAL.com, gann-list@cs.iastate.edu, ml@ics.uci.edu, neuron-request@CATTELL.psych.upenn.edu, TIERRA@life.slhs.udel.edu, alife@cognet.ucla.edu, cells@tce.ing.uniroma1.it, cellular-automata@think.com, ep-list@magenta.me.fau.edu, ga-list@aic.nrl.navy.mil, genetic-programming@cs.stanford.edu Cc: R.Poli@cs.bham.ac.uk Subject: PhD Studentships Dear Colleagues, Could you please circulate the following advertisement for PhD studentships? Thank you very much, Riccardo Poli Dr. Riccardo Poli E-mail: R.Poli@cs.bham.ac.uk School of Computer Science Telephone: +44-121-414-3739 The University of Birmingham Fax: +44-121-414-4281 Edgbaston, Birmingham B15 2TT, UK ---------------------------------------------------------------------- The University of Birmingham School of Computer Science Research Studentships in ~~~~~~~~ ~~~~~~~~~~~~ EMERGENT AND EVOLUTIONARY BEHAVIOUR, INTELLIGENCE, AND COMPUTATION (EEBIC) Applications are invited for a number of Studentships for full-time PhD research in the School of Computer Science to carry out research within the recently founded EEBIC group. The group's research interests include: evolutionary computation (e.g. genetic algorithms and genetic programming), emergent behaviour, emergent intelligence (e.g. emergent communication), emergent computation and artificial life and their practical applications in hard engineering problems. The members of the group, at Birmingham and elsewhere, are active researchers in Artificial Intelligence, Engineering or Psychology with a variety of different backgrounds including Biology, Computer Science, Engineering, Psychology and Philosophy. In addition to EEBIC, the research experience of the members of the group includes computer vision, neural nets, signal processing, intelligent autonomous agents, hybrid inference systems, computer emotions, logic and many others. The group interacts very closely with the Cognition and Affect group led by Aaron Sloman who is a member of both groups. (For more information see URLs: ftp://ftp.cs.bham.ac.uk/pub/groups/cog_affect and http://www.cs.bham.ac.uk/~axs .) The successful applicants will join the group's effort to explore EEBIC in many interesting directions (from engineering to psychology, from new practical applications to new theoretical frameworks). They will have constant interaction and collaboration with the other members of the group. In addition to the usual requirements of possessing a good honours degree (equivalent to a first or upper second class degree in a UK university) and being EU residents, the successful candidates will need to be particularly open minded to the cross-fertilisation in the group deriving from the different backgrounds and experience of the members. Additional information about how to apply and about the School is available via WWW from URL: http://www.cs.bham.ac.uk Informal enquiries about the EEBIC group can be directed to Riccardo Poli Phone: +44-121-414-3739 Fax: +44-121-414-4281 Email: R.Poli@cs.bham.ac.uk Enquiries concerning the Cognition and Affect group may be sent to Aaron Sloman Phone: +44-121-414-4775 Fax: +44-121-414-4281 Email: A.Sloman@cs.bham.ac.uk For any other queries contact our research students' admission tutor: Dr Peter Hancox Email: P.J.Hancox@cs.bham.ac.uk From eric@research.nj.nec.com Tue Jul 18 15:23:27 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Tue, 18 Jul 95 15:23:24 -0500; AA18195 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Tue, 18 Jul 95 15:23:14 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11485; 17 Jul 95 17:38:39 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11483; 17 Jul 95 17:28:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08840; 17 Jul 95 17:27:31 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa21191; 17 Jul 95 16:26:08 EDT Received: from zingo.nj.nec.com by EDRC.CMU.EDU id aa18405; 17 Jul 95 16:25:50 EDT Received: by zingo (940816.SGI.8.6.9/YDL1.4-910307.16) id QAA06036(zingo); Mon, 17 Jul 1995 16:23:22 -0400 Received: by yin (940816.SGI.8.6.9/cliff's joyful mailer #2) id QAA00552(yin); Mon, 17 Jul 1995 16:23:22 -0400 Date: Mon, 17 Jul 1995 16:23:22 -0400 From: "Eric B. Baum" Message-Id: <199507172023.QAA00552@yin> To: Connectionists@cs.cmu.edu Subject: Job Announcement Cc: eric@research.nj.nec.com Programmer Wanted. Prerequisites: Experience in getting large programs to work. Some mathematical sophistication. E.g. at least equivalent of a good undergraduate degree in math, physics, theoretical computer science or related field. Salary: Depends on experience. Job: Implementing various novel algorithms. The previous holder of this position (Charles Garrett) implemented our new Bayesian approach to games, with striking success. We are now engaged in an effort to produce a world championship chess program based on these methods and several new ideas regarding learning. The chess program is being written in Modula 3. Experience in Modula 3 is useful but not essential so long as you are willing to learn it. Other projects may include TD learning, GA's, etc. To access papers on our approach to games, and get some idea of general nature of other projects, (e.g. a paper on GA's Garrett worked on) see my home page http://www.neci.nj.nec.com:80/homepages/eric/eric.html A paper on classifier-like learning systems with Garrett will appear there RSN (but don't wait to apply). The successful applicant will (a)have experience getting *large* programs to *work*, (b) be able to understand the papers on my home page and convert them to computer experiments. These projects are at the leading edge of basic research in algorithms/cognition/learning, so expect the work to be both interesting and challenging. Term-contract position. To apply please send cv, cover letter and list of references to: eric@research.nj.nec.com .ps or plain text please! NOTE- EMAIL ONLY. Hardcopy, e.g. US mail or Fedex etc, will not be opened. Equal Opportunity Employer M/F/D/V ------------------------------------- Eric Baum NEC Research Institute, 4 Independence Way, Princeton NJ 08540 PHONE:(609) 951-2712, FAX:(609) 951-2482, Inet:eric@research.nj.nec.com From read@bohr.neusc.bcm.tmc.edu Tue Jul 18 15:23:29 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Tue, 18 Jul 95 15:23:26 -0500; AA18201 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Tue, 18 Jul 95 15:23:24 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa11529; 17 Jul 95 18:34:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa11527; 17 Jul 95 18:26:59 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08911; 17 Jul 95 18:26:21 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa23608; 17 Jul 95 18:17:52 EDT Received: from DIRAC.NEUSC.BCM.TMC.EDU by EDRC.CMU.EDU id aa18904; 17 Jul 95 18:17:06 EDT Received: from hermes.bcm.tmc.edu by dirac.neusc.bcm.tmc.edu via ESMTP (950215.SGI.8.6.10/930416.SGI.AUTO) for <@DIRAC.NEUSC.bcm.tmc.edu:Connectionists@CS.CMU.EDU> id RAA09483; Mon, 17 Jul 1995 17:16:58 -0500 Received: from bcm.tmc.edu (bcm.tmc.edu [128.249.2.1]) by hermes.bcm.tmc.edu (8.6.11/8.6.11) with SMTP id RAA20657 for <@DIRAC.NEUSC.bcm.tmc.edu:Connectionists@CS.CMU.EDU>; Mon, 17 Jul 1995 17:16:58 -0500 Received: from BOHR.NEUSC.BCM.TMC.EDU (bohr.neusc.bcm.tmc.edu [128.249.25.33]) by bcm.tmc.edu (8.6.11/8.6.6) with SMTP id RAA18122 for <@DIRAC.NEUSC.bcm.tmc.edu:Connectionists@CS.CMU.EDU>; Mon, 17 Jul 1995 17:16:57 -0500 Received: by BOHR.NEUSC.BCM.TMC.EDU (950215.SGI.8.6.10/930416.SGI.AUTO) id RAA01629; Mon, 17 Jul 1995 17:17:15 -0500 From: "P. Read Montague" Message-Id: <9507171717.ZM1627@bohr.bcm.tmc.edu> Date: Mon, 17 Jul 1995 17:17:14 -0500 X-Mailer: Z-Mail (3.2.0 26oct94 MediaMail) To: Connectionists@cs.cmu.edu Subject: Postdoctoral position Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii POSTDOCTORAL POSITION IN THEORETICAL NEUROSCIENCE A postdoctoral fellowship in theoretical neuroscience is available through the newly formed Center for Theoretical Neuroscience at Baylor College of Medicine. The position will focus on theoretical problems, however, all potential projects will be closely allied with ongoing experiments in the laboratories of Drs John Maunsell and Nikos Logothetis in the Division of Neuroscience at Baylor. Current interests include the role of attention in visual perception, the neural basis for decision-making, and the neural basis for object recognition. The successful candidate will have a strong knowledge in basic neurobiology combined with quantitative background in physics, computing, or engineering. Fellows will receive stipends commensurate with their background and qualifications. Send curriculum vitae, research interests, and the names of three references to: Dr. P. Read Montague Division of Neuroscience, Baylor College of Medicine, 1 Baylor Plaza, Houston, TX 77030 email: read@bohr.bcm.tmc.edu -- P. Read Montague Division of Neuroscience Baylor College of Medicine 1 Baylor Plaza, Houston, TX 77030 read@bohr.bcm.tmc.edu From read@bohr.neusc.bcm.tmc.edu Wed Jul 19 01:50:25 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 01:50:23 -0500; AA22373 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 01:50:21 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00304; 18 Jul 95 14:21:53 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00302; 18 Jul 95 13:47:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09727; 18 Jul 95 13:47:05 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa06143; 18 Jul 95 11:51:17 EDT Received: from DIRAC.NEUSC.BCM.TMC.EDU by RI.CMU.EDU id aa10197; 18 Jul 95 11:50:15 EDT Received: from hermes.bcm.tmc.edu by dirac.neusc.bcm.tmc.edu via ESMTP (950215.SGI.8.6.10/930416.SGI.AUTO) for <@DIRAC.NEUSC.bcm.tmc.edu:connectionists@cs.cmu.edu> id KAA11708; Tue, 18 Jul 1995 10:50:06 -0500 Received: from bcm.tmc.edu (bcm.tmc.edu [128.249.2.1]) by hermes.bcm.tmc.edu (8.6.11/8.6.11) with SMTP id KAA28646 for <@DIRAC.NEUSC.bcm.tmc.edu:connectionists@cs.cmu.edu>; Tue, 18 Jul 1995 10:50:05 -0500 Received: from BOHR.NEUSC.BCM.TMC.EDU (bohr.neusc.bcm.tmc.edu [128.249.25.33]) by bcm.tmc.edu (8.6.11/8.6.6) with SMTP id KAA02993 for <@DIRAC.NEUSC.bcm.tmc.edu:connectionists@cs.cmu.edu>; Tue, 18 Jul 1995 10:50:03 -0500 Received: by BOHR.NEUSC.BCM.TMC.EDU (950215.SGI.8.6.10/930416.SGI.AUTO) id KAA02788; Tue, 18 Jul 1995 10:50:21 -0500 From: "P. Read Montague" Message-Id: <9507181050.ZM2786@bohr.bcm.tmc.edu> Date: Tue, 18 Jul 1995 10:50:21 -0500 X-Mailer: Z-Mail (3.2.0 26oct94 MediaMail) To: connectionists@cs.cmu.edu Subject: Posdoctoral Position Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii POSTDOCTORAL POSITION IN THEORETICAL NEUROSCIENCE A postdoctoral fellowship in theoretical neuroscience is available through the newly formed Center for Theoretical Neuroscience at Baylor College of Medicine. The position will focus on theoretical problems, however, all potential projects will be closely allied with ongoing experiments in the laboratories of Drs John Maunsell and Nikos Logothetis in the Division of Neuroscience at Baylor. Current interests include the role of attention in visual perception, the neural basis for decision-making, and the neural basis for object recognition. The successful candidate will have a strong knowledge in basic neurobiology combined with quantitative background in physics, computing, or engineering. Fellows will receive stipends commensurate with their background and qualifications. Send curriculum vitae, research interests, and the names of three references to: -- P. Read Montague Division of Neuroscience Baylor College of Medicine 1 Baylor Plaza, Houston, TX 77030 read@bohr.bcm.tmc.edu From koiran@ICSI.Berkeley.EDU Wed Jul 19 18:23:30 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 18:23:27 -0500; AA04388 Message-Id: <9507192323.AA11875@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 18:23:24 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00847; 18 Jul 95 21:30:30 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00845; 18 Jul 95 21:22:33 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10114; 18 Jul 95 21:17:46 EDT Return-Path: From: Pascal Koiran Date: Tue, 18 Jul 1995 17:22:10 -0700 To: Connectionists@cs.cmu.edu Subject: Re: "Orthogonality" of the generalizers being combined Cc: koiran@ICSI.Berkeley.EDU In my previous message on combinining generalizers, Manfred Warmuth should have been added to the list of "expert advice" researchers. I apologize for that omission. (note that I do not claim that the list is complete now !) Pascal Koiran. From giles@research.nj.nec.com Wed Jul 19 18:23:33 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 18:23:28 -0500; AA04390 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 18:23:26 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00879; 18 Jul 95 21:36:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00876; 18 Jul 95 21:30:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10105; 18 Jul 95 21:17:02 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ab13022; 18 Jul 95 18:31:25 EDT Received: from zingo.nj.nec.com by CS.CMU.EDU id aa05469; 18 Jul 95 18:30:29 EDT Received: by zingo (940816.SGI.8.6.9/YDL1.4-910307.16) id SAA21404(zingo); Tue, 18 Jul 1995 18:27:58 -0400 Received: by telluride (940816.SGI.8.6.9/cliff's joyful mailer #2) id SAA08663(telluride); Tue, 18 Jul 1995 18:27:57 -0400 Date: Tue, 18 Jul 1995 18:27:57 -0400 From: Lee Giles Message-Id: <199507182227.SAA08663@telluride> To: connectionists@cs.cmu.edu Subject: TR announcment - long-term dependencies The following Technical Report is available via the University of Maryland Department of Computer Science and the NEC Research Institute archives: _____________________________________________________________________________ LEARNING LONG-TERM DEPENDENCIES IS NOT AS DIFFICULT WITH NARX RECURRENT NEURAL NETWORKS Technical Report UMIACS-TR-95-78 and CS-TR-3500, Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742 Tsungnan Lin{1,2}, Bill G. Horne{1}, Peter Tino{1,3}, C. Lee Giles{1,4} {1}NEC Research Institute, 4 Independence Way, Princeton, NJ 08540 {2}Department of Electrical Engineering, Princeton University, Princeton, NJ 08540 {3}Dept. of Computer Science and Engineering, Slovak Technical University, Ilkovicova 3, 812 19 Bratislava, Slovakia {4}UMIACS, University of Maryland, College Park, MD 20742 ABSTRACT It has recently been shown that gradient descent learning algorithms for recurrent neural networks can perform poorly on tasks that involve long- term dependencies, i.e. those problems for which the desired output depends on inputs presented at times far in the past. In this paper we explore the long-term dependencies problem for a class of architectures called NARX recurrent neural networks, which have power ful representational capabilities. We have previously reported that gradient descent learning is more effective in NARX networks than in recurrent neural network architectures that have ``hidden states'' on problems includ ing grammatical inference and nonlinear system identification. Typically, the network converges much faster and generalizes better than other net works. The results in this paper are an attempt to explain this phenomenon. We present some experimental results which show that NARX networks can often retain information for two to three times as long as conventional recurrent neural networks. We show that although NARX networks do not circumvent the problem of long-term dependencies, they can greatly improve performance on long-term dependency problems. We also describe in detail some of the assumption regarding what it means to latch information robustly and suggest possible ways to loosen these assumptions. ---------------------------------------------------------------------------------- ---------------------------------------------------------------------------------- http://www.neci.nj.nec.com/homepages/giles.html http://www.cs.umd.edu/TRs/TR-no-abs.html or ftp://ftp.nj.nec.com/pub/giles/papers/UMD-CS-TR-3500.long-term.dependencies.narx.ps.Z ------------------------------------------------------------------------------------ -- C. Lee Giles / NEC Research Institute / 4 Independence Way Princeton, NJ 08540, USA / 609-951-2642 / Fax 2482 URL http://www.neci.nj.nec.com/homepages/giles.html == From maass@igi.tu-graz.ac.at Wed Jul 19 18:23:34 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 18:23:30 -0500; AA04399 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 18:23:27 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa00887; 18 Jul 95 21:43:20 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa00882; 18 Jul 95 21:32:51 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10110; 18 Jul 95 21:17:13 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa13115; 18 Jul 95 18:35:25 EDT Received: from figids03.tu-graz.ac.at by RI.CMU.EDU id aa12048; 18 Jul 95 18:35:07 EDT Received: from localhost by figids03 with SMTP id AA12291 (5.67b/IDA-1.5t for Connectionists@cs.cmu.edu); Wed, 19 Jul 1995 00:36:21 +0200 Message-Id: <199507182236.AA12291@figids03> To: Connectionists@cs.cmu.edu Subject: 2 papers on spiking neurons in neuroprose Date: Wed, 19 Jul 95 00:36:21 +0200 From: Wolfgang Maass X-Mts: smtp First paper: ************ FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/maass.spiking-details.ps.Z The file maass.spiking-details.ps.Z is now available for copying from the Neuroprose repository. This is a 41-page long paper. Hardcopies are not available. LOWER BOUNDS FOR THE COMPUTATIONAL POWER OF NETWORKS OF SPIKING NEURONS by Wolfgang Maass Institute for Theoretical Computer Science Technische Universitaet Graz A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at Abstract: We explore the computational power of formal models for networks of spiking neurons (often referred to as "integrate-and-fire neurons"). These neural net models are closer related to computations in biological neural systems than the more traditional models, since they allow an encoding of information in the timing of single spikes (not just in firing rates). Our formal model is closely related to the "spike-response model" that was previously introduced by Gerstner and van Hemmen. It turns out that the structure of computations in models for networks of spiking neurons is quite different from that of computations in analog (sigmoidal) neural nets. In particular it is shown in our paper in a rigorous way that simple operations on phase-differences between spike-trains provide a very powerful computational tool, that can in principle be used to carry out highly complex computations on a small network of spiking neurons. We also show in this paper that rather weak assumptions about the shape of response-and threshold-functions of spiking neurons are sufficient in order to employ them for such computations. An extended abstract of this paper had already been posted in November 1994 (it appears in the Proc. of NIPS 94). In the meantime many have asked me for details of the constructions, and hence I am now also posting in neuroprose this detailed version (which appears in Neural Computation). A companion paper with detailed proofs for the upper bounds, will become available in the fall. ---------------------------------------------------------------------- Second paper: ************* FTP-host: archive.cis.ohio-state.edu FTP-filename: /pub/neuroprose/maass.shape.ps.Z The file maass.shape.ps.Z is now available for copying from the Neuroprose repository. This is a 6-page long paper. Hardcopies are not available. ON THE RELEVANCE OF THE SHAPE OF POSTSYNAPTIC POTENTIALS FOR THE COMPUTATIONAL POWER OF SPIKING NEURONS by Wolfgang Maass and Berthold Ruf Institute for Theoretical Computer Science Technische Universitaet Graz A-8010 Graz, Austria e-mail: maass@igi.tu-graz.ac.at bruf@igi.tu-graz.ac.at Abstract: Recently one has started to explore silicon models for networks of spiking neurons, where one employs rectangular (i.e. piecewise constant) pulses instead of the "smooth" excitatory postsynaptic potentials (EPSP's) that are employed by biological neurons. We show in this paper that models of spiking neurons that employ rectangular pulses (EPSP's) have substantial computational power, and we give a precise characterization of their computational power in terms of a common benchmark model from computer science (random access machine). This characterization allows us to prove the following somewhat surprising result: Models of networks of spiking neurons with rectangular pulses are from the computational point of view STRICTLY WEAKER than models with "smooth" EPSP's of the type as they are observed in biological neurons. ************ How to obtain a copy of the first paper ************* Via Anonymous FTP: unix> ftp archive.cis.ohio-state.edu Name: anonymous Password: (type your email address) ftp> cd pub/neuroprose ftp> binary ftp> get maass.spiking-details.ps.Z ftp> quit unix> uncompress maass.spiking-details.ps.Z unix> lpr maass.spiking-details.ps (or what you normally do to print PostScript) For the second paper proceed analogously (but with filename maass.shape.ps.Z). From phkywong@uxmail.ust.hk Wed Jul 19 23:51:24 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 23:51:19 -0500; AA06746 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 23:51:17 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa01961; 19 Jul 95 10:23:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa01959; 19 Jul 95 10:11:26 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10834; 19 Jul 95 10:10:47 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa20090; 19 Jul 95 3:48:23 EDT Received: from uxmail.ust.hk by RI.CMU.EDU id aa13826; 19 Jul 95 3:47:51 EDT Received: from phsu2.ust.hk by uxmail.ust.hk id <18930-1>; Wed, 19 Jul 1995 15:44:46 +0800 From: "Dr. Michael Wong" To: Connectionists@cs.cmu.edu Subject: Paper on Neural Dynamic Routing Available Cc: phfelix@uxmail.ust.hk Message-Id: <95Jul19.154446+0800_hkt.18930-1+4@uxmail.ust.hk> Date: Wed, 19 Jul 1995 15:44:44 +0800 FTP-host: physics.ust.hk FTP-file: pub/kymwong/rout.ps.gz The following paper, presented at IWANNT*95, is now available via anonymous FTP. (8 pages long) ============================================================================ Decentralized Neural Dynamic Routing in Circuit-Switched Networks W. K. Felix Lor and K. Y. Michael Wong Department of Physics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong. E-mail address: phfelix@usthk.ust.hk, phkywong@usthk.ust.hk Clear Water Bay, Kowloon, Hong Kong. ABSTRACT We use a Simplex centralized algorithm to dynamically distribute telephonic traffic among alternate routes in circuit-switched networks according to the fluctuating number of free circuits and the evolving call attempts. It generates examples for training localized Neural controllers. Simulations shows that the decentralized Neural approach has a comparable performance in blocking probability with Maximum Free Circuit (MFC) and gives a surpassing performance in crankback. ============================================================================ FTP instructions: unix> ftp physics.ust.hk Name: anonymous Password: your full email address ftp> cd pub/kymwong ftp> get rout.ps.gz ftp> quit unix> gunzip rout.ps.gz unix> lpr rout.ps From uzimmer@informatik.uni-kl.de Wed Jul 19 23:51:25 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 23:51:21 -0500; AA06748 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 23:51:18 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02188; 19 Jul 95 16:19:09 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02185; 19 Jul 95 15:54:55 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11033; 19 Jul 95 15:53:51 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa27310; 19 Jul 95 11:55:16 EDT Received: from stepsun.uni-kl.de by CS.CMU.EDU id aa11999; 19 Jul 95 11:52:36 EDT Received: from uklirb.informatik.uni-kl.de by stepsun.uni-kl.de id ab12344; 19 Jul 95 17:49 MET DST Received: from ag-vp-file-server.informatik.uni-kl.de by uklirb.uklirb.informatik.uni-kl.de id aa10863; 19 Jul 95 17:47 MET DST Subject: Paper available on "Minimal Qualitative Topologic World Models for Mobile Robots" To: connectionists@cs.cmu.edu, crr@ireq-robot.hydro.qc.ca From: "Uwe R. Zimmer" Date: Wed, 19 Jul 95 17:47:03 +0100 Reply-To: uzimmer@informatik.uni-kl.de Message-Id: <950719.174703.269@informatik.uni-kl.de> Paper available via WWW / FTP: keywords: mobile robots, exploration, world modelling, self-localization, artificial neural networks ------------------------------------------------------------------ Minimal Qualitative Topologic World Models for Mobile Robots ------------------------------------------------------------------ Uwe R. Zimmer (submitted for publication) World models for mobile robots as introduced in many projects, are mostly redundant regarding similar situations detected in different places. The present paper proposes a method for dynamic generation of a minimal world model based on these redundancies. The technique is an extention of the qualitative topologic world modelling methods. As a central aspect the reliability regarding error-tolerance and stability will be emphasized. The proposed technique demands very low constraints on the kind and quality of the employed sensors as well as for the kinematic precision of the utilized mobile platform. Hard realtime constraints can be handled due to the low computational complexity. The principal discussions are supported by real-world experiments with the mobile robot "ALICE". (5 pages - 928 KB) for the WWW-link: ------------------------------------------------------------------ http://ag-vp-www.informatik.uni-kl.de/Projekte/ALICE/ abs.Minimal.html ------------------------------------------------------------------ for the homepage of the author (including more reports): ------------------------------------------------------------------ http://ag-vp-www.informatik.uni-kl.de/Leute/Uwe/ ------------------------------------------------------------------ or for the ftp-server hosting the file: ------------------------------------------------------------------ ftp://ag-vp-ftp.informatik.uni-kl.de/Public/Neural_Networks/ Reports/Zimmer.Minimal.ps.Z ------------------------------------------------------------------ ----------------------------------------------------- ----- Uwe R. Zimmer --- University of Kaiserslautern - Computer Science Department | 67663 Kaiserslautern - Germany | ------------------------------.--------------------------------. Phone:+49 631 205 2624 | Fax:+49 631 205 2803 | ------------------------------.--------------------------------. http://ag-vp-www.informatik.uni-kl.de/Leute/Uwe/ | From arbib@pollux.usc.edu Wed Jul 19 23:51:27 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 23:51:23 -0500; AA06754 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 23:51:20 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab02188; 19 Jul 95 16:20:21 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab02185; 19 Jul 95 15:54:57 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11037; 19 Jul 95 15:54:14 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa28169; 19 Jul 95 12:49:43 EDT Received: from pollux.usc.edu by EDRC.CMU.EDU id aa28335; 19 Jul 95 12:48:24 EDT Received: (arbib@localhost) by pollux.usc.edu (8.6.12/8.6.4) id JAA28988 for Connectionists@cs.cmu.edu; Wed, 19 Jul 1995 09:48:14 -0700 Date: Wed, 19 Jul 1995 09:48:14 -0700 From: "Michael A. Arbib" Message-Id: <199507191648.JAA28988@pollux.usc.edu> To: Connectionists@cs.cmu.edu Subject: Positions Available: VISUALIZATION FOR BRAIN RESEARCH ABOUT THE USC BRAIN PROJECT Professors Michael Arbib (Director), Michel Baudry, Theodore Berger, Peter Danzig, Shahram Ghandeharizadeh, Scott Grafton, Dennis McLeod, Thomas McNeill, Larry Swanson, and Richard Thompson are about to start the second year of a major grant from the Human Brain Project (a consortium of federal agencies led by the National Institute of Mental Health) for a 5 year project, "Neural Plasticity: Data and Computational Structures" to be conducted at the University of Southern California. The Project will combine research on databases with the development of tools for database construction and data recovery from multiple databases, simulation tools, and visualization tools for both rat neuroanatomy and human brain imaging. These tools will be used to construct databases for research at USC and elsewhere on mechanisms of neural plasticity in basal ganglia, cerebellum, and hippocampus. The grant will also support a core of neuroscience research linked to several ongoing research programs to explore how experiments can be enhanced when coupled to databases enriched with powerful tools for modeling and visualization. The project is a major expression of USC's approach to the study of the brain which locates neuroscience in the context of a broad interdisciplinary program in Neural, Informational, and Behavioral Sciences (NIBS). The status of our work may be viewed on WWW at http://www-hbp.usc.edu:8376/HBP/Home.html ABOUT THE POSITIONS The grant and related funding will allow us to hire two computer professionals to help us develop visualization tools for the USC Brain Project. VISUALIZATION PROGRAMMER: Three years experience programming and developing graphical software. UNIX, C++, DBMS experience. Internet protocols also desirable. Ability link visualization software with object based data base and simulation tools. Background in neuroscience is not required but proven communication skills and ability to analyze scientific data are valuable. IMAGE ANALYSIS DEVELOPER: Three years experience programming and developing graphical software. UNIX, C++, DBMS experience. Internet protocols also desirable. Emphasis on streamlining existing image analysis code and developing new algorithms for warping 3D data sets. Additional ability to manage the growth of a large archive of MRI and functional image data sets is valuable. Send CV, references, and letter addressing above qualifications to Paulina Tagle, Center for Neural Engineering, USC, Los Angeles, CA 90089-2520; Fax (213) 740-5687; paulina@pollux.usc.edu. USC is an equal opportunity employer. From pihong@merlot.cse.ogi.edu Wed Jul 19 23:51:29 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 23:51:25 -0500; AA06764 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 23:51:22 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02204; 19 Jul 95 16:30:11 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02198; 19 Jul 95 16:09:56 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11076; 19 Jul 95 16:09:11 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id ab02443; 19 Jul 95 16:03:25 EDT Received: from cse.ogi.edu by CS.CMU.EDU id aa14839; 19 Jul 95 16:01:15 EDT Received: from merlot.cse.ogi.edu by church.cse.ogi.edu with smtp (Smail3.1.29.1 #2) id m0sYfIW-000KlOC; Wed, 19 Jul 95 13:00 PDT Received: by merlot.cse.ogi.edu (NX5.67e/NX3.0S) id AA08786; Wed, 19 Jul 95 13:00:44 -0700 Message-Id: <9507192000.AA08786@merlot.cse.ogi.edu> Content-Type: text/plain Mime-Version: 1.0 (NeXT Mail 3.3 v118.2) Received: by NeXT.Mailer (1.118.2) From: Hong Pi Date: Wed, 19 Jul 95 13:00:42 -0700 To: anncourse@merlot.cse.ogi.edu Subject: Neural Network Course (Announcement) Reply-To: Hong Pi Oregon Graduate Institute of Science & Technology, Office of Continuing Education, offers the short course: NEURAL NETWORKS: ALGORITHMS AND APPLICATIONS September 25-29, 1995, at the OGI campus near Portland, Oregon. Course Organizer: John E. Moody Lead Instructor: Hong Pi With Lectures By: Todd K. Leen John E. Moody Thorsteinn S. Rognvaldsson Eric A. Wan Artificial neural networks (ANN) have emerged as a new information processing technique and an effective computational model for solving pattern recognition and completion, feature extraction, optimization, and function approximation problems. This course introduces participants to the neural network paradigms and their applications in pattern classification; system identification; signal processing and image analysis; control engineering; diagnosis; time series prediction; and financial analysis and trading. An introduction to fuzzy logic and fuzzy control systems is also given. Designing a neural network application involves steps from data preprocessing to network tuning and selection. This course, with many examples, application demos and hands-on lab practice, will familiarize the participants with the techniques necessary for building successful applications. About 50 percent of the class time is assigned to lab sessions. The simulations will be based on Matlab, the Matlab Neural Net Toolbox, and other software running on Windows-NT workstations. Prerequisites: Linear algebra and calculus. Previous experience with using Matlab is helpful, but not required. Who will benefit: Technical professionals, business analysts, financial market practitioners, and other individuals who wish to gain a basic understanding of the theory and algorithms of neural computation and/or are interested in applying ANN techniques to real-world, data-driven modeling problems. Course Objectives: After completing the course, students will: - Understand the basic neural networks paradigms - Be familiar with the range of ANN applications - Have a good understanding of the techniques for designing successful applications - Gain hands-on experience with ANN modeling. Course Outline (8:30am - 5:00pm September 25 - 28, and 8:30am - 12:30am September 29): Neural Networks: Biological and Artificial Biological inspirations. Basic models of a neuron. Types of architectures and learning paradigms. Simple Perceptrons and Adalines Decision surfaces. Linear separability. Perceptron learning rules. Linear units. Gradient descent learning. Multi-Layer Feed-Forward Networks I Multi-Layer perceptrons. Back-propagation learning. Generalization. Early Stopping via validation. Momentum and adaptive learning rate. Examples and applications. Multi-Layer Feed-Forward Networks II Newton's method. Conjugate gradient. Levenburg-Marquardt. Radial basis function networks. Projection pursuit regression. Neural Networks for Pattern Recognition and Classification Bayes decision theory. The Bayes risk. Non-neural and neural methods for classification. Neural networks as estimators of the posterior probability. Methods for improving the classification performance. Benchmark tests of neural networks vs. other methods. Some applications. Improving the Generalization Performance Model bias and model variance. Weight decay. Regularizers. Optimal brain surgeon. Learning from hints. Sensitivity analysis. Input variable selection. The delta-test. Time Series Prediction: Classical and Nonlinear Approaches Linear time series models. Simple nonlinear models. Recurrent network models and training algorithms. Case studies: sunspots, economic forecasting. Self-Organized Networks and Unsupervised Learning K-means clustering. Kohonen feature maps. Learning vector quantization. Adaptive principal components analysis. Neural Network for Adaptive Control What is control. Heuristic, open loop, and inverse control. Feedback algorithms for control. Neural network feedback control. Reinforcement learning. Survey of Neural Network Applications in Financial Markets Bond and stock valuation. Currency rate forecasting. Trading systems. Commodity price forecasting. Risk management. Option pricing. Fuzzy Systems Fuzzy logic. Fuzzy control systems. Adaptive fuzzy and neural-fuzzy. About the Instructors Todd K. Leen is associate professor of Computer Science and Engineering at Oregon Graduate Institute of Science & Technology. He received his Ph.D. in theoretical Physics from the University of Wisconsin in 1982. From 1982-1987 he worked at IBM Corporation, and then pursued research in mathematical biology at Good Samaritan Hospital's Neurological Sciences Institute. He joined OGI in 1989. Dr. Leen's current research interests include neural learning, algorithms and architectures, stochastic optimization, model constraints and pruning, and neural and non-neural approaches to data representation and coding. He is particularly interested in fast, local modeling approaches, and applications to image and speech processing. Dr. Leen served as theory program chair for the 1993 Neural Information Processing Systems (NIPS) conference, and workshops chair for the 1994 NIPS conference. John E. Moody is associate professor of Computer Science and Engineering at Oregon Graduate Institute of Science & Technology. His current research focuses on neural network learning theory and algorithms in it's many manifestations. He is particularly interested in statistical learning theory, the dynamics of learning, and learning in dynamical contexts. Key application areas of his work are adaptive signal processing, adaptive control, time series analysis, forecasting, economics and finance. Moody has authored over 35 scientific papers, more than 25 of which concern the theory, algorithms, and applications of neural networks. Prior to joining the Oregon Graduate Institute, Moody was a member of the Computer Science and Neuroscience faculties at Yale University. Moody received his Ph.D. and M.A. degrees in Theoretical Physics from Princeton University, and graduated Summa Cum Laude with a B.A. in Physics from the University of Chicago. Hong Pi is a senior research associate at Oregon Graduate Institute. He received his Ph.D. in theoretical physics from University of Wisconsin in 1989. Prior to joining OGI in 1994 he had been a postdoctoral fellow and research scientist in Lund University, Sweden. His research interests include nonlinear modeling, neural network algorithms and applications. Thorsteinn S. Rognvaldsson received the Ph.D. degree in theoretical physics from Lund University, Sweden, in 1994. His research interests are Neural Networks for prediction and classification. He is currently a postdoctoral research associate at Oregon Graduate Institute. Eric A. Wan, Assistant Professor of Electrical Engineering and Applied Physics, Oregon Graduate Institute of Science & Technology, received his Ph.D. in electrical engineering from Stanford University in 1994. His 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, speech enhancement, system identification, and adaptive control. He is a member of IEEE, INNS, Tau Beta Pi, Sigma Xi, and Phi Beta Kappa. For a complete course brochure contact: Linda M. Pease, Director Office of Continuing Education Oregon Graduate Institute of Science & Technology PO Box 91000 Portland, OR 97291-1000 +1-503-690-1259 +1-503-690-1686 (fax) e-mail: continuinged@admin.ogi.edu WWW home page: http://www.ogi.edu ^*^*^*^*^*^*^*^*^*^*^**^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^* Linda M. Pease, Director lpease@admin.ogi.edu Office of Continuing Education Oregon Graduate Institute of Science & Technology 20000 N.W. Walker Road, Beaverton OR 97006 USA (shipping) P.O. Box 91000, Portland, OR 97291-1000 USA (mailing) +1-503-690-1259 +1-503-690-1686 fax "The future belongs to those who believe in the beauty of their dreams" -Eleanor Roosevelt ^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^*^* From jagota@next1.msci.memst.edu Wed Jul 19 23:51:30 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 19 Jul 95 23:51:28 -0500; AA06770 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 19 Jul 95 23:51:26 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02301; 19 Jul 95 18:04:49 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02299; 19 Jul 95 17:57:59 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11223; 19 Jul 95 17:57:34 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id ab04552; 19 Jul 95 17:44:07 EDT Received: from next1.msci.memphis.edu by EDRC.CMU.EDU id aa29836; 19 Jul 95 17:41:28 EDT Received: by next1 id AA22908 (5.65c/IDA-1.4.4 for connectionists@cs.cmu.edu); Wed, 19 Jul 1995 16:41:23 -0500 Date: Wed, 19 Jul 1995 16:41:23 -0500 From: Arun Jagota Message-Id: <199507192141.AA22908@next1> To: connectionists@cs.cmu.edu Subject: Notes for HKP on WWW Dear Connectionists: I am offering a set of handwritten transparencies, in electronic scanned-in form, for portions of the book "Introduction to the Theory of Neural Computation", Hertz, Krogh, and Palmer, on the World Wide Web as follows: http://www.msci.memphis.edu/~jagota You are welcome to make transparencies off them for instructional purposes, or print them off for some other reason. Or simply browse using Netscape, Mosaic, etc. Some features are a little awkward. First, they are all hand-written (in color) and quite unpolished. Second, each transparency is scanned into a raw image and therefore retrieving it takes some time. In all, there are about 110 of them, and they cover the following topics: ------------------------------------ ONE Introduction TWO The Hopfield Model 2.1 Associative Memories and Energy Function: 2.2 Hebb Rule and Capacity 2.3 Stochastic Networks THREE Extensions of the Hopfield Model 3.1 Continuous-Valued Units FOUR Optimization Problems 4.1 Mapping Problems to Hopfield Network 4.2 The Weighted Matching Problem 4.3 Graph Bipartitioning FIVE Simple Perceptrons 5.1 Feed-Forward Networks 5.2 Threshold Units 5.3 Perceptron Learning Rule Proof of Convergence 5.4 Continuous Units 5.5 Capacity of the Simple Perceptron SIX Multi-Layer Networks 6.1 Back-Propagation 6.2 Variations on Back-Propagation 6.3 Examples and Applications ------------------------------------ Let me also add that version 2 of the HKP exercises (very slightly refined and expanded from version 1) is available from the same ftp location as earlier: ftp ftp.cs.buffalo.edu > cd users/jagota > get HKP.ps Arun Jagota, Math Sciences, University of Memphis From KOKINOV@BGEARN.BITNET Fri Jul 21 01:50:16 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 21 Jul 95 01:50:13 -0500; AA19910 Message-Id: <9507210650.AA04525@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 21 Jul 95 01:50:10 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa01125; 19 Jul 95 1:00:37 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa01123; 19 Jul 95 0:53:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa10242; 19 Jul 95 0:52:57 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa17700; 19 Jul 95 0:49:59 EDT Received: from helios.edvz.univie.ac.at by CS.CMU.EDU id aa07529; 19 Jul 95 0:49:16 EDT Received: from BGEARN.ACAD.BG by AWIUNI11.EDVZ.UniVie.AC.AT (IBM VM SMTP V2R2) with BSMTP id 1726; Wed, 19 Jul 95 06:48:57 MEZ Received: from BGEARN (NJE origin KOKINOV@BGEARN) by BGEARN.ACAD.BG (LMail V1.2a/1.8a) with BSMTP id 3327; Tue, 18 Jul 1995 16:59:52 +0300 Date: Tue, 18 Jul 95 16:59:14 BG From: Boicho Kokinov Subject: 10 scholarschips in Cognitive Science To: Kokinov 10 scholarships are available to successful candidates for the Graduate Program in Cognitive Science at NBU for candidates from Eastern and Central Europe. The scholarschips have been provided by the Soros Foundation. NEW BULGARIAN UNIVERSITY Department of Cognitive Science Admission to the Graduate Program in Cognitive Science is open till July 30. It offers the following degrees: Post-Graduate Diploma, M.Sc., Ph.D. FEATURES Teaching in English both in the regular courses at NBU and in the intensive courses at the Annual International Summer Schools. Strong interdisciplinary program covering Psychology, Artificial Intelligence, Neurosciences, Linguistics, Philosophy, Mathematics, Methods. Theoretical and experimental research in integration of the symbolic and connectionist approaches, emergent hybrid cognitive architectures, models of memory and reasoning, analogy, vision, imagery, agnosia, language and speech processing, aphasia. Advisors: at least two advisors with different backgrounds, possibly one external international advisor. International dissertation committee. INTERNATIONAL ADVISORY BOARD Elizabeth Bates (UCSD, USA), Amedeo Cappelli (CNR, Italy), Cristiano Castelfranchi (CNR, Italy), Daniel Dennett (Tufts University, USA), Charles De Weert (University of Nijmegen, Holland), Christian Freksa (Hamburg University, Germany), Dedre Gentner (Northwestern University, USA), Christopher Habel (Hamburg University, Germany), Douglas Hofstadter (Indiana University, USA), Joachim Hohnsbein (University of Dortmund, Germany), Keith Holyoak (UCLA, USA), Mark Keane (Trinity College, Ireland), Alan Lesgold (University of Pittsburg, USA), Willem Levelt (Max-Plank Institute of Psycholinguistics, Holland), Ennio De Renzi (University of Modena, Italy), David Rumelhart (Stanford University, USA), Richard Shiffrin (Indiana University, USA), Paul Smolensky (University of Colorado, USA), Chris Thornton (University of Sussex, England ), Carlo Umilta' (University of Padova, Italy) ADDMISSION REQUIREMENTS B.Sc. degree in psychology, computer science, linguistics, philosophy, neurosciences, or related fields. Good command of English. Address: Cognitive Science Department, New Bulgarian University, 21 Montevideo Str. Sofia 1635, Bulgaria, tel.: (+3592) 55-80-65 fax: (+3592) 54-08-02 e-mail: cogs@adm.nbu.bg or kokinov@bgearn.acad.bg From mao@almaden.ibm.com Fri Jul 21 01:50:21 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 21 Jul 95 01:50:17 -0500; AA19916 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 21 Jul 95 01:50:15 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02279; 19 Jul 95 17:32:19 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02277; 19 Jul 95 17:22:45 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa11162; 19 Jul 95 17:22:11 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa03817; 19 Jul 95 17:08:43 EDT Received: from [198.4.83.131] by CS.CMU.EDU id aa15575; 19 Jul 95 17:07:31 EDT Received: from ALMADEN by almaden.ibm.com (IBM VM SMTP V2R2) with BSMTP id 9316; Wed, 19 Jul 95 14:05:00 PDT Received: by ALMADEN (XAGENTA 3.0) id 3077; Wed, 19 Jul 1995 14:04:59 -0700 Received: by powerocr.almaden.ibm.com (AIX 3.2/UCB 5.64/4.03) id AA21208; Wed, 19 Jul 1995 14:07:04 -0700 Date: Wed, 19 Jul 1995 14:07:04 -0700 From: mao@almaden.ibm.com Mmdf-Warning: Parse error in original version of preceding line at DST.BOLTZ.CS.CMU.EDU Message-Id: <9507192107.AA21208@powerocr.almaden.ibm.com> To: connectionists@cs.cmu.edu Subject: Call for papers, IEEE Trans. NNs Special Issues on ANNs and PR Cc: jain@cps.msu.edu, mao@almaden.ibm.com CALL FOR PAPERS IEEE Transactions on Neural Networks Special Issue on Artificial Neural Networks and Pattern Recognition Tentative Publication Date: November 1996 Artificial neural networks (ANN) have now been recognized as powerful and economical tools for solving a large variety of problems in a number of scientific and engineering disciplines. The literature on neural networks is enormous consisting of a large number of books, journals and conference proceedings, and new commercial software and hardware products. A large portion of the research and development on ANNs is devoted to solving pattern recognition problems. Pattern recognition (PR) is a relatively mature discipline. Over the past 50 years, a number of different paradigms (statistical, syntactic and neural networks) have been utilized for solving a variety of recognition problems. But, real-world recognition problems are sufficiently difficult so that a single paradigm is not "optimal" for different recognition problems. As a result, successful recognition systems based either on statistical approach or neural networks exist in limited domains (e.g., handprinted character recognition and isolated word speech recognition). There is a close relationship between some of the popular ANN models and statistical pattern recognition (SPR) approaches. Quite often, these relationships are either not known to researchers or not fully exploited to build "hybrid" recognition systems. In spite of this close resemblance between ANN and SPR, ANNs have provided a variety of novel or supplementary approaches for pattern recognition tasks. More noticeably, ANNs have provided architectures on which many classical SPR algorithms (e.g., tree classifiers, principal component analysis, K-means clustering) can be mapped to facilitate hardware implementation. On the other hand, ANNs can derive benefit from some well-known results in SPR (e.g., Bayes decision theory, nearest neighbor rules, curse of dimensionality and Parzen window classifier). The purpose of this special issue is to increase the awareness of researchers and practitioners of pattern recognition about the common links between ANNs and SPR. This is likely to lead to more communication and cooperative work between the two research communities. Such an effort will not only avoid repetitious work but, more importantly, will stimulate and motivate individual disciplines. It is our hope that this special issue will lead to a synergistic approach which combines the strengths of ANN and SPR in order to achieve a significantly better performance for complex pattern recognition problems. Specific topics of interest include, but are not limited to: o Old and new links between ANNs and SPR (e.g., Adaptive Mixture of Expert (AME) and Hierarchical Mixture of Experts (HME) versus traditional decision trees, recurrent ANNs and time-delay ANNs versus Hidden Markov Models, generalization ability in ANNs versus curse of dimensionality). o Comparative studies of ANN and SPR approaches that lead to useful guidelines in practice (e.g., under what conditions does one approach exhibit superiority to the other?). o New ANN models for PR. -- representation/feature extraction (compression rate, invariance, robustness, and efficiency) using ANNs. -- supervised classification. -- clustering/unsupervised classification. o Combination of ANN and SPR classifiers/estimators, and features extracted using traditional PR approaches and ANNs. o Hybrid (using ANNs and traditional PR approaches) systems for solving real-world PR problems (e.g., face recognition, cursive handwriting recognition, and speech recognition). Although these topics cover a broad area of research, we encourage papers that explore the relationship between ANNs and traditional PR. Authors should relate their work with both the PR and ANN literature. Papers should also emphasize results that have been or can be potentially applied to "real world" applications; they should include evaluations through either experimentation, simulation, analysis and/or experience. Guest Editors: -------------- Professor Anil K. Jain Dr. Jianchang Mao Department of Computer Science Image and Multimedia Systems, DPE/803 A714 Wells Hall IBM Almaden Research Center Michigan State University 650 Harry Road East Lansing, MI 48824, USA San Jose, CA 95120, USA Email: jain@cps.msu.edu Email: mao@almaden.ibm.com Fax: 517-432-1061 Fax: 408-927-3497 Instructions for submitting papers: ----------------------------------- Manuscripts must not have been previously published or currently submitted for publication elsewhere. Each manuscript should be no more than 35 pages (double space, 12 point font) including all text, references, and illustrations. Each copy of the manuscript should include a title page containing title, authors' names and affiliations, postal and email addresses, telephone numbers and Fax numbers, a 300-word abstract and a list of keywords identifying the central issues of the manuscript's contents. Please submit six copies of your manuscript to either of the guest editors by January 5, 1996. --------------- From tamayo@Think.COM Fri Jul 21 01:50:23 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 21 Jul 95 01:50:20 -0500; AA19922 Message-Id: <9507210650.AA04535@lucy.cs.wisc.edu> Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 21 Jul 95 01:50:18 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa03777; 20 Jul 95 15:17:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa03774; 20 Jul 95 14:57:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa12313; 20 Jul 95 14:57:35 EDT From: Pablo Tamayo Date: Wed, 12 Jul 95 18:17:36 EDT To: Connectionists-Request@cs.cmu.edu Subject: Commercial Apps/Machine Learning Developer Wanted For more than a decade, Thinking Machines Corporation has been one of the world's leading computer companies in advancing the capability and use of high performance computing. Through its unique expertise in parallel process technology it has developed three generations of world-class hardware, software, and complementary support systems. Now we are beginning a new and exciting growth strategy to open up our technology to new hardware platforms and application environments. Thinking Machines is uniquely positioned to deliver state-of-the-art, cost effective systems on standard industry platforms. Join us as we unleash the power of parallel processing software. Thinking Machines Corporation has several openings for talented engineers, including: Commercial Applications Researcher/Developers Design, implementation and support of software for commercial applications involving machine learning (Neural Nets, CART, MBR, GA), statistics (SAS), and parallel processing of massive databases. Requirements: MS/PhD in CS/EE or equivalent. Expertise in C/UNIX, HPC and commercial databases (SQL, Oracle, etc.) If you are interested in this position or want information on other openings that are currently available, please send your resume to: Rick Pitman Thinking Machines Corporation 245 First Street Cambridge, MA 02142 Internet address: rickp@think.com Phone: (617) 234-3016 Fax: (617) 234-4421 An Equal Opportunity Employer The Connection Machine is a registered trademark of Thinking Machines Corporation. UNIX is a registered trademark of UNIX Systems Laboratories, Inc. From poole@cs.ubc.ca Fri Jul 21 23:21:03 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 21 Jul 95 23:20:59 -0500; AA03568 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 21 Jul 95 23:20:56 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05318; 21 Jul 95 16:52:15 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05312; 21 Jul 95 16:24:27 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa13371; 21 Jul 95 16:23:56 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa05905; 21 Jul 95 12:57:56 EDT Received: from grolsch-2.cs.ubc.ca by EDRC.CMU.EDU id aa09404; 21 Jul 95 12:56:58 EDT Received: (from ean@localhost) by grolsch.cs.ubc.ca (8.6.10/8.6.9) id JAA15283 for Connectionists@CS.CMU.EDU; Fri, 21 Jul 1995 09:56:03 -0700 X400-Received: by /PRMD=ca/ADMD=telecom.canada/C=ca/; Relayed; Fri, 21 Jul 1995 9:56:01 UTC-0700 Date: Fri, 21 Jul 1995 9:56:01 UTC-0700 X400-Originator: poole@cs.ubc.ca X400-Recipients: non-disclosure:; X400-Content-Type: P2-1984 (2) X400-Mts-Identifier: [/PRMD=ca/ADMD=telecom.canada/C=ca/;950721095601] Content-Identifier: 6538 From: David Poole To: Connectionists@cs.cmu.edu Message-Id: <"6538*poole@cs.ubc.ca"@MHS> Subject: 11th Conference on Uncertainty in AI, August 1995 Mime-Version: 1.0 (Generated by Ean X.400 to MIME gateway) The Conferences in Uncartianty in AI are the premier forum for work on reasoning under uncertainty (including probabilistic and other formalisms for uncertainty, representations for uncertainty, such as Bayesian networks, algorithms for inference under uncertainty and learning under ucertainty). The 11th Conference on Uncertianty in AI will be held in Montreal, 18-20 August 1995 (just before IJCAI-95). For full details including registration information and an online proceedings see the URL: http://www.cs.ubc.ca/spider/poole/UAI95.html The program for UAI-95 is as follows: UAI-95 - 11th Conference on Uncertainty in AI McGill University, Montreal, Quebec, 18-20 August 1995 =================================== Final Program =================================== ============================== Friday 18 August Overview ============================== 08:45 -- 09:00 Opening remarks 09:00 -- 10:15 Invited talk #1 (Haussler) 10:15 -- 10:30 Break 10:30 -- 12:30 Presentation session #1 12:30 -- 14:00 Lunch 14:00 -- 16:00 Poster session #1 16:00 -- 16:15 Break 16:30 -- 18:30 Presentation session #2 ================================ Saturday 19 August Overview ================================ 09:00 -- 10:30 Invited talk #2 (Jordan) + panel discussion 10:30 -- 10:45 Break 10:45 -- 12:45 Presentation session #3 12:45 -- 14:30 Lunch 14:30 -- 16:00 Invited talk #3 (Subrahmanian) 16:00 -- 16:15 Break 16:15 -- 18:15 Presentation session #4 ================================ Sunday 20 August Overview ================================ 09:00 -- 10:30 Invited talk #4 (Shafer) + panel discussion 10:30 -- 10:45 Break 10:45 -- 12:45 Presentation session #5 12:45 -- 14:30 Lunch 14:30 -- 16:00 Poster session #2 16:00 -- 16:15 Break 16:15 -- 18:15 Presentation session #6 ============================================== Invited talks ============================================== #1 Haussler "Hidden Markov and Related Statistical Models: How They Have Been Applied to Biosequence Analysis" #2 Jordan (with panel on learning) "A Few Relevant Ideas from Statistics, Neural Networks, and Statistical Mechanics" #3 Subrahamanian "Uncertainty in Deductive Databases" #4 Shafer (with panel on causality) "The Multiple Causal Interpretation of Bayes Nets" ================================================= Presentation session #1 ================================================= Wellman/Ford/Larson PATH PLANNING UNDER TIME-DEPENDENT UNCERTAINTY Horvitz/Barry DISPLAY OF INFORMATION FOR TIME-CRITICAL DECISION MAKING Pearl/Robins PROBABILISTIC EVALUATION OF SEQUENTIAL PLANS FROM CAUSAL MODELS WITH HIDDEN VARIABLES Haddawy/Doan/Goodwin EFFICIENT DECISION-THEORETIC PLANNING: TECHNIQUES AND EMPIRICAL ANALYSIS Fargier/Lang/Clouaire/Schiex A CONSTRAINT SATISFACTION FRAMEWORK FOR DECISION UNDER UNCERTAINTY ================================================= Presentation session #2 ================================================= Xu/Smets GENERATING EXPLANATIONS FOR EVIDENTIAL REASONING ========> Best student paper <=========== Meek CAUSAL INFERENCE AND CAUSAL EXPLANATION WITH BACKGROUND KNOWLEDGE ========> Best student paper <=========== Cayrac/Dubois/Prade PRACTICAL MODEL-BASED DIAGNOSIS WITH QUALITATIVE POSSIBILISTIC UNCERTAINTY Srinivas/Horvitz EXPLOITING SYSTEM HIERARCHY TO COMPUTE REPAIR PLANS IN PROBABILISTIC MODEL-BASED DIAGNOSIS Balke/Pearl COUNTERFACTUALS AND POLICY ANALYSIS IN STRUCTURAL MODELS ================================================= Presentation session #3 ================================================= Jensen CAUTIOUS PROPAGATION IN BAYESIAN NETWORKS Darwiche STRONG CONDITIONING ALGORITHMS FOR EXACT AND APPROXIMATE INFERENCE IN CAUSAL NETWORKS ========> Best student paper <=========== Draper CLUSTERING WITHOUT (THINKING ABOUT) TRIANGULATION ========> Best student paper <=========== Goldszmidt FAST BELIEF UPDATE USING ORDER-OF-MAGNITUDE PROBABILITIES ========> Best student paper <=========== Harmanec TOWARD A CHARACTERIZATION OF UNCERTAINTY MEASURE FOR THE DEMPSTER-SHAFER THEORY ========> Best student paper <=========== ================================================= Presentation session #4 ================================================= Dubois/Prade NUMERICAL REPRESENTATION OF ACCEPTANCE Grosof TRANSFORMING PRIORITIZED DEFAULTS AND SPECIFICITY INTO PARALLEL DEFAULTS Weydert DEFAULTS AND INFINITESIMALS DEFEASIBLE INFERENCE BY NONARCHIMEDEAN ENTROPY-MAXIMIZATION Benferhat/Saffiotti/Smets BELIEF FUNCTIONS AND DEFAULT REASONING Ngo/Haddawy/Helwig A THEORETICAL FRAMEWORK FOR CONTEXT-SENSITIVE TEMPORAL PROBABILITY MODEL CONSTRUCTION WITH APPLICATION TO PLAN PROJECTION ========================================== Presentation session #5 ========================================== Campos/Moral INDEPENDENCE CONCEPTS FOR CONVEX SETS OF PROBABILITIES Geiger/Heckerman A CHARACTERIZATION OF THE DIRICHLET DISTRIBUTION THROUGH GLOBAL AND LOCAL INDEPENDENCE Spirtes DIRECTED CYCLIC GRAPHICAL REPRESENTATIONS OF FEEDBACK MODELS Pynadath/Wellman ACCOUNTING FOR CONTEXT IN PLAN RECOGNITION, WITH APPLICATION TO TRAFFIC MONITORING Srinivas MODELING FAILURE PRIORS AND PERSISTENCE IN MODEL-BASED DIAGNOSIS ========================================== Presentation session #6 ========================================== Poole EXPLOITING THE RULE STRUCTURE FOR DECISION MAKING WITHIN THE INDEPENDENT CHOICE LOGIC Krause/Fox/Judson IS THERE A ROLE FOR QUALITATIVE RISK ASSESSMENT? Srinivas POLYNOMIAL ALGORITHM FOR COMPUTING THE OPTIMAL REPAIR STRATEGY IN A SYSTEM WITH INDEPENDENT COMPONENT FAILURES Boldrin/Sossai AN ALGEBRAIC SEMANTICS FOR POSSIBILISTIC LOGIC Hajek/Godo/Esteva FUZZY LOGIC AND PROBABILITY ============================================================== Poster session #1 ============================================================== 1. Jack Breese, Russ Blake. AUTOMATING COMPUTER BOTTLENECK DETECTION WITH BELIEF NETS 2. Wray L. Buntine CHAIN GRAPHS FOR LEARNING 3. J.L. Castro, J.M. Zurita AN APPROACH TO GET THE STRUCTURE OF A FUZZY RULE UNDER UNCERTAINTY 4. Tom Chavez, Ross Shachter DECISION FLEXIBILITY 5. Arthur L. Delcher, Adam Grove, Simon Kasif, Judea Pearl LOGARITHMIC-TIME UPDATES AND QUERIES IN PROBABILISTIC NETWORKS 6. Eric Driver, Darryl Morrell CONTINUOUS BAYESIAN NETWORKS 7. Nir Friedman, Joseph Y. Halpern PLAUSIBILITY MEASURES: A USER'S GUIDE 8. David Galles, Judea Pearl TESTING IDENTIFIABILITY OF CAUSAL EFFECTS 9. Steve Hanks, David Madigan, Jonathan Gavrin PROBABILISTIC TEMPORAL REASONING WITH ENDOGENOUS CHANGE 10. David Heckerman BAYESIAN METHODS FOR LEARNING CAUSAL NETWORKS 11. Eric Horvitz, Adrian Klein STUDIES IN FLEXIBLE LOGICAL INFERENCE: A DECISION-MAKING PERSPECTIVE 12. George John, Pat Langley ESTIMATING CONTINUOUS DISTRIBUTIONS IN BAYESIAN CLASSIFIERS 13. Uffe Kjaerulff HUGS: COMBINING EXACT INFERENCE AND GIBBS SAMPLING IN JUNCTION TREES 14. Prakash P. Shenoy A NEW PRUNING METHOD FOR SOLVING DECISION TREES AND GAME TREES 15. Peter Spirtes, Christopher Meek, Thomas Richardson CAUSAL INFERENCE IN THE PRESENCE OF LATENT VARIABLES AND SELECTION BIAS 16. Nic Wilson AN ORDER OF MAGNITUDE CALCULUS 17. S.K.M. Wong, C.J. Butz, Y. Xiang A METHOD FOR IMPLEMENTING A PROBABILISTIC MODEL AS A RELATIONAL DATABASE
18. Y. Xiang OPTIMIZATION OF INTER-SUBNET BELIEF UPDATING IN MULTIPLY SECTIONED BAYESIAN NETWORKS 19. Nevin Lianwen Zhang INFERENCE WITH CAUSAL INDEPENDENCE IN THE CPSC NETWORK =============================================== Poster Session #2 =============================================== 1. Fahiem Bacchus, Adam Grove GRAPHICAL MODELS FOR PREFERENCE AND UTILITY 2. Enrique Castillo, Remco R. Bouckaert, Jose Maria Sarabia, ERROR ESTIMATION IN APPROXIMATE BAYESIAN BELIEF NETWORK INFERENCE 3. David Maxwell Chickering A NEW CHARACTERIZATION OF EQUIVALENT BAYESIAN NETWORK STRUCTURES 4. Marek J. Druzdzel, Linda C. van der Gaag ELICITATION OF PROBABILITIES: COMBINING QUALITATIVE AND QUANTITATIVE INFORMATION 5. Kazuo J. Ezawa, Til Schuermann LEARNING SYSTEM: A RARE BINARY OUTCOME WITH MIXED DATA STRUCTURES 6. David Heckerman, Dan Geiger LEARNING BAYESIAN NETWORKS: A UNIFICATION FOR DISCRETE AND GAUSSIAN DOMAINS 7. David Heckerman, Ross Shachter A DEFINITION AND GRAPHICAL REPRESENTATION FOR CAUSALITY 8. Mark Hulme IMPROVED SAMPLING FOR DIAGNOSTIC REASONING IN BAYESIAN NETWORK 9. Ali Jenzarli INFORMATION/RELEVANCE INFLUENCE DIAGRAMS 10. Keiji Kanazawa, Daphne Koller, Stuart Russell STOCHASTIC SIMULATION ALGORITHMS FOR DYNAMIC PROBABILISTIC NETWORKS 11. Grigoris I. Karakoulas PROBABILISTIC EXPLORATION IN PLANNING WHILE LEARNING 12. Alexander V. Kozlov, Jaswinder Pal Singh APPROXIMATE PROBABILISTIC INFERENCE IN BELIEF NETWORKS 13. Michael L. Littman, Thomas L. Dean, Leslie Pack Kaelbling ON THE COMPLEXITY OF SOLVING MARKOV DECISION PROBLEMS 14. Chris Meek STRONG-COMPLETENESS AND FAITHFULNESS IN BAYES NETWORKS 15. Simon Parsons REFINING REASONING IN QUALITATIVE PROBABILISTIC NETWORKS 16. Judea Pearl ON THE TESTABILITY OF CAUSAL MODELS WITH LATENT AND INSTRUMENTAL VARIABLES 17. Gregory Provan ABSTRACTION IN BELIEF NETWORKS: THE ROLE OF INTERMEDIATE STATES IN DIAGNOSTIC REASONING 18. Marco Valtorta, Young-Gyun Kim ON THE DETECTION OF CONFLICTS IN DIAGNOSTIC BAYESIAN NETWORKS USING ABSTRACTION ----------------------------------------------------------------------------- David Poole, Office: +1 (604) 822-6254 Department of Computer Science, Fax: +1 (604) 822-5485 University of British Columbia, Email: poole@cs.ubc.ca 2366 Main Mall, URL: http://www.cs.ubc.ca/spider/poole Vancouver, B.C., Canada V6T 1Z4 FTP: ftp://ftp.cs.ubc.ca/ftp/local/poole From linster@katla.harvard.edu Fri Jul 21 23:21:04 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 21 Jul 95 23:21:01 -0500; AA03570 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 21 Jul 95 23:20:58 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05462; 21 Jul 95 19:45:57 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05459; 21 Jul 95 19:37:33 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa13492; 21 Jul 95 19:36:38 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa19251; 20 Jul 95 15:06:21 EDT Received: from katla.harvard.edu by CS.CMU.EDU id aa24794; 20 Jul 95 15:05:37 EDT Date: Thu, 20 Jul 1995 15:04:35 -0400 (EDT) From: Christiane Linster To: connectionists@cs.cmu.edu Cc: linster@katla.harvard.edu Subject: postdoc grant (fwd) Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII *********************************************************** ************************************************************ CNRS-INRA Laboratoire de Neurobiologie Comparee des Invertebres Postdoctoral Research Fellowship Applications are invited for a year fellowship, from non-french citizen and qualified researcher with experience in Molecular neurobiology to investigate olfaction in insects. Applications, including a CV with the names of two referees should be sent urgently (before August 31, 1995) to: Dr C. MASSON LNCI BP 23 F - 91 440 Bures-sur-Yvette Tel. and fax : 33 1 69 07 20 59 E-mail : masson@inra.jouy.fr From srikanth@diamond.cau.auc.edu Sat Jul 22 11:58:07 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 22 Jul 95 11:58:01 -0500; AA07233 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 22 Jul 95 11:57:59 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05305; 21 Jul 95 16:41:00 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05300; 21 Jul 95 16:23:36 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa13363; 21 Jul 95 16:23:20 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa22683; 20 Jul 95 17:56:57 EDT Received: from etta.auc.edu by CS.CMU.EDU id aa26766; 20 Jul 95 17:55:56 EDT Received: from diamond.cau.auc.edu ([144.125.96.203]) by auc.edu (4.1/SMI-4.1) id AA02192; Thu, 20 Jul 95 14:04:56 EDT Received: by diamond.cau.auc.edu (4.1/SMI-4.1) id AA02884; Thu, 20 Jul 95 13:50:07 EDT From: srikanth@diamond.cau.auc.edu Message-Id: <9507201750.AA02884@diamond.cau.auc.edu> Subject: Call For Papers FUZZ-IEEE 1996 To: connectionists@cs.cmu.edu Date: Thu, 20 Jul 95 13:50:07 EDT X-Mailer: ELM [version 2.3 PL11] ANNOUNCEMENT AND PRELIMINARY CALL FOR PAPERS IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS New Orleans, September 8-11, 1996 PAPERS DUE: January 31, 1996 NOTIFICATION OF ACCEPTANCE: April 15, 1996 FINAL PAPERS DUE: June 15, 1996 SPECIAL SESSION / TUTORIAL PROPOSALS December 1, 1995 The program committee invites potential authors to submit papers dealing with any aspect of research and applications related to the use of fuzzy models. Papers must be written in English and received by 1/31/96. Six copies of the paper must be submitted. The paper may not exceed 7 pages including figures, tables and references. Papers should be prepared on 8.5" X 11" white paper with 1" margins on all sides, one column format in Times or similar style, 10 points or larger, and printed on one side of the paper only. Please include title, author names(s) and affliation on top of the first page followed by an abstract. FAX submissions are NOT acceptable. Please indicate the corresponding author with their email address where possible. Please send submissions prior to the deadline to Dr. Don Kraft, Program Committee Chair Computer Science Department, Louisiana State University Baton Rouge, LA 70803-4020 email: kraft@bit.csc.lsu.edu phone:504-388-2253 SEE ALSO : http://jasper.cau.auc.edu/fuzz_ieee1.html for more details about FUZZ-IEEE '96 and New Orleans! ------------------------------------------------------------------------------ GENERAL CHAIR PROGRAM CHAIR Fredrick E. Petry Donald Kraft Tulane University Louisiana State University New Orleans, LA Baton Rouge, LA petry@rex.cs.tulane.edu kraft@bit.csc.lsu.edu PUBLICITY CHAIRS Roy George, R. Srikanth Jim Keller Clark Atlanta University University of Missouri Atlanta, GA Columbia, MO roy@diamond.cau.auc.edu srikanth@diamond.cau.auc.edu PROCEEDINGS CHAIR Padmini Srinivasan University of SW Louisiana Lafayette, LA EXHIBITS CHAIR Valarie Cross V. Ganesh Miami University Allied Signal Oxford, OH Morristown, NJ FINANCE CHAIR Sujeet Shenoi University of Tulsa Tulsa, OK From jbower@bbb.caltech.edu Sat Jul 22 19:09:56 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 22 Jul 95 19:09:53 -0500; AA09141 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 22 Jul 95 19:09:51 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05483; 21 Jul 95 19:57:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05475; 21 Jul 95 19:50:16 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa13516; 21 Jul 95 19:49:55 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa12713; 21 Jul 95 19:48:35 EDT Received: from smaug-gw.caltech.edu by CS.CMU.EDU id aa07926; 21 Jul 95 19:47:50 EDT Received: from bbb.caltech.edu (smaug.bbb.caltech.edu) by gateway.bbb.caltech.edu (4.1/SMI-4.0) id AA22386; Fri, 21 Jul 95 16:56:07 PDT Received: from [131.215.137.84] (gatorbox4.bbb.caltech.edu) by bbb.caltech.edu (4.1/SMI-4.1) id AA22523; Fri, 21 Jul 95 16:55:49 PDT Date: Fri, 21 Jul 95 16:55:48 PDT Message-Id: <9507212355.AA22523@bbb.caltech.edu> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: Connectionists@cs.cmu.edu From: jbower@bbb.caltech.edu Subject: Journal of Computational Neurscience Vol.II(2) The JOURNAL OF COMPUTATIONAL NEUROSCIENCE From neurons to behavior: a journal at the interface between experimental and theoretical neuroscience... CONTENTS, VOLUME II, ISSUE 2 Dynamic Modification of Dendritic Cable Properties and Synaptic Transmission by Voltage-Gated Potassium C.J. Wilson. Electrical Consequences of Spine Dimensions in a Model of Cortical Spiny Stellate Cell Completely Reconstructed Serial Thin Sections I. Segev, A. Friedman, E.L. White, M.J. Gutnick. The Electric Image in Weakly Electric Fish: I. A Data Based Model of Waveform Generation in the Gymnotus Carapo A. Caputi and R. Budelli. Temporal Encoding in Nervous Systems: a Rigorous Definition F.Theunissen, J.P. Miller. Editorial introducing the Bulletin Board. Bulletin; D. Glanzman ************************************** SUBSCRIPTIONS: Volume 2, 1995 (4 issues): Institutional rate: $270.00 US Individual rate: $75.00 US PLEASE CONTACT: Kluwer Academic Publishers Order Department P.O. Box 358, Accord Station Hingham, MA 02108-0358 USA Phone: (617) 871-6600, Fax: (617) 871-6528 E-mail: kluwer@wkap.com Please refer to the KLUWER ACADEMIC PUBLISHERS INFORMATION SERVER at GOPHER.WKAP.NL for Call for Papers, Aims and Scope and additional information. *************************************** James M. Bower Division of Biology Mail code: 216-76 Caltech Pasadena, CA 91125 (818) 395-6817 (818) 449-0679 FAX NCSA Mosaic addresses for: laboratory http://www.bbb.caltech.edu/bowerlab GENESIS: http://www.bbb.caltech.edu/GENESIS science education reform http://www.caltech.edu/~capsi