neuron@HPLPM.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") (11/27/90)
Neuron Digest Monday, 26 Nov 1990 Volume 6 : Issue 68 Today's Topics: Re: Neural Chess, I have developed one evolution of "wetware" recognition of signatures off-line motor neuron control models homo trans sapiens Seismic analysis want NETtalk phoneme data Bay Area SIGINS Contact Re: Neuron Digest V6 #66 call for papers for COLT '91 Postdoctoral Positions Copenhagen Optimization Conference Send submissions, questions, address maintenance and requests for old issues to "neuron-request@hplabs.hp.com" or "{any backbone,uunet}!hplabs!neuron-request" Use "ftp" to get old issues from hplpm.hpl.hp.com (15.255.176.205). ------------------------------------------------------------ Subject: Re: Neural Chess, I have developed one From: David Kanecki <kanecki@vacs.uwp.wisc.edu> Date: Tue, 13 Nov 90 22:00:38 -0600 Based upon the discussion in the previous neuron digest a computer chess program using neural networks was postulated. From initial programming started in August of 1989 I was able to complete a neural network chess program on March 20th, 1990. The program was able to win one game from me while losing three. The main advantage of this program was that it could work with different chess variations and generate a move response in less than one minute on a CP/M machine. Namely, the osborne 1. Thus, intelligence beats brawn. The basis of the program was to use an actual neural network system from biology. In this case I choose the the animal group Chordata. And, the subclass mamallia. The program was built so that it had a sympathetic and parasympathetic network. From this the program was able to generate good moves without having to use the 'brawn' of the minimax technique. And, with this initial program it is very easy for me to try other levels of chess and more advanced versions of chess, ala Star Trek chess. In conclusion I believe that the purpose of the microcomputer revolution was not to duplicate what could be done on big whales of mainframes, but by using intelligence a smaller, leaner, and more innovative way of thinking and action would become common place. Also, I have developed a neural simulator where I am offering free evaluations for a limited time. Either send me a description of data or coded data where I will send an evaluation by the program back. To obtain an example on how to present data to the netowrk contact me at the bitnet address below. Any comments or feedback wowuld be welcomed. David H. Kanecki, Bio. Sci., A.C.S. P.O. Box 93 Kenosha, WI 53141 bitnet: kanecki@vacs.uwp.wisc.edu ------------------------------ Subject: evolution of "wetware" From: "Bruce E. Nevin" <bnevin@ccb.bbn.com> Date: Wed, 14 Nov 90 08:10:25 -0500 > From: Volume 6 : Issue 66 > Subject: Re: Evolution > From: UAP001%DDOHRZ11.BITNET@CUNYVM.CUNY.EDU, UAP001 at DDOHRZ11 > . . . Development of the cortex probably stopped abruptly (after a spurt > of remarkable growth) about 100,000 years ago. . . . > the reasonable assumption is that the wetware hasn't changed much since There is a great deal of variation in the way human CNSs are "wired," none of which would leave fossil traces. There is every reason to assume such variation has always existed. Variation is a necessary condition for selection and evolutionary change. Whether or not the variants show up in the fossil record is a limitation of our evidence, not a constraint on evolution as an ongoing process. ------------------------------ Subject: recognition of signatures off-line From: "Grup VLSI de la U. Autonoma de Barcelona" <IINF4%ccuab1.uab.es@CUNYVM.CUNY.EDU> Date: Thu, 15 Nov 90 15:22:00 +0000 I'm working in subjects related to pattern recognition. My interest is focussed in writing recognition and more concretely in the recognition of signatures off-line. I would like to compare the performance of neural networks in front of standard techniques. Does anybody have information about neural networks designed to deal with this problem? Thank you in advance. F. Navarro Universitat Autonoma de Barcelona Departament d'informatica 08193 Bellaterra Barcelona, Spain E-mail: IINF4@EBCCUAB1.bitnet ------------------------------ Subject: motor neuron control models From: Dr. Jack Meador <meador@eecs.wsu.edu> Date: Thu, 15 Nov 90 11:30:20 -0800 I am collecting information regarding the supervisory control of stretch reflex to manipulate muscle movement. References to people working with or literature addressing the following topics is requested: 1. muscle models 2. spinal motor neural circuit models 3. supervisory control of motor circuits for muscle movement 4. bionic limbs 5. software which demonstrates any or all of the above Please send your responses to the address listed below. I will make the results of this inquiry available to those requesting it at a later date. Thank you for your responses. Jack Meador / EECS Dept. / Washington State University / meador@eecs.wsu.edu [[ Editor's Note: I hope Jack will share his results with the in this Digest as well... -PM ]] ------------------------------ Subject: homo trans sapiens From: sct60a.sunyct.edu!sct60a.sunyct.edu!stu@sct60a.sunyct.edu (Stu Card) Date: Thu, 15 Nov 90 20:33:39 -0500 I fear that Elan Moritz may suffer from the widespread misconception that natural evolution is purposive: that a species develops new traits in order to achieve some goal. This misconception is promoted by the use of phrases such as 'adaptive strategy' by people who should know better. Here is the low down on evolution, according to Darwin (who may admittedly not have the last word), as I understand it: 1) THINGS HAPPEN. All kinds of events simply TAKE PLACE, according to whatever combination of determinism and randomness rules the universe. 2) As a result of things happening, SOME FORMS CHANGE. It is the FORM and not the SUBSTANCE that matters. Individual atoms of carbon, nitrogen, etc. are replaced continuously in living organisms, yet the identity and nature of the organism are not called into question, because the FORM has remained the same. 3) Some of these changes result in the form being altered so SEVERELY that we consider it to have become a completely different form (such as a rotting corpse rather than a living organism). 4) Some of these changes, however, preserve the attributes of the form which WE CONSIDER to be important, and change only little things. If these little changes are passed along to the offspring of the form, and if these changes result in more of those offspring surviving future rounds of THINGS HAPPENING (more, as compared with the same forms without those little changes), without sufferring the SEVERE CHANGES noted above, then we call the little changes SUCCESSFUL MUTATIONS. 5) Sex, viral infection, bacterial gene-swapping and possibly other processes permit the alteration of forms through the exchange and permutation of CODES of form which have already proven successful. Thus successful codes from different sources may combine to produce still more-successful forms. The point is, NONE OF THIS IS PURPOSIVE. IT JUST HAPPENS! All we mean by 'successful' is that the form sticks around for a relatively long time with relatively little change to those attributes of form which WE CONSIDER to be important (defining) characteristics of that form. Now to address the real issue: How are the proposed characteristics of homo trans sapiens going to cause more of his offspring to survive and successfully reproduce? I fully agree that it would be NICE to have more brainpower. However, given the mutual support systems (technological, economic, political, etc.) developed by domesticated primates ('humans' or 'homo sapiens'), it would appear that more brainpower is not going to give an individual a significantly higher probability of reaching reproductive age, nor a higher number of offspring. Please, somebody, prove me wrong! My conclusions are depressing. NOTE: What I have said only pertains to NATURAL evolution -- bioengineers, genetecists, cyborg-builders, roboticists, etc. NEED NOT BE CONCERNED and indeed should plug away, as they seem to be our only hope! Oh, sorry, accidentally left out you mystics... :-E/> Stu Card (nobody important) stu@sct60a.sunyct.edu ------------------------------ Subject: Seismic analysis From: erik@goofy.llnl.gov (Erik Johannson) Date: Fri, 16 Nov 90 10:24:09 -0800 Jerry - My colleague Farid Dowla is involved in seismic analysis, and has done significant work in the field using neural networks and conventional signal processing methods. You can reach him at: Farid Dowla Lawrence Livermore National Laboratory PO Box 808, L-205 Livermore, CA 94550 (415) 423-7579 dowla@s75.es.llnl.gov Sincerely, Erik M. Johansson erik@goofy.llnl.gov ------------------------------ Subject: want NETtalk phoneme data From: DAVID@VSMJC.SCRI.FSU.EDU Date: Sun, 18 Nov 90 21:26:40 -0500 I am trying to locate the data that Sejnowski and Rosenberg used to train their NETtalk network. If anyone has this data or knows a machine that I could anonymously ftp it from, I would greatly appreciate hearing about it. Alternatively, if someone out there has the e-mail address(es) of the two authors, I could contact them directly. -David LaSalle Email: dlasalle@evax0.eng.fsu.edu USnail: Dept of Elec. Eng. Florida State Univ. P.O. Box 2175 Tallahassee, FL 32316-2175 ------------------------------ Subject: Bay Area SIGINS Contact From: "Neuron-Digest Moderator -- Peter Marvit" <neuron@hplabs.hpl.hp.com> Date: Tue, 20 Nov 90 18:34:09 -0800 [[ Editor's Note: This fellow telephoned me today. He has just returned from six months in Germany doing neural net research. He had volunteered to the the coordinator of the SIGINS for the San Francisco Bay area, but discovered that the contact information (submitted by someone else) had erroneously included the wrong telephone number. I'm submitting this note on his behalf until he is able to get his new office back on line. Welcome back, Andras! -PM ]] Greetings, I am Dr. Andras Pellionisz and am the San Francisco Bay Area coordinator for the SIGINS (Special Interest Group for Neural Systems) of the INNS (International Neural Network Society). You can contact me for membership and meeting information at the following telephone numbers: Work: 415/604-4821 FAX: 415/604-0046 I do not have a regular e-mail address yet since I just arrived back at NASA's Ames Research Center, but can be reached through a colleague's account at lichunwu@pioneer.arc.nasa.gov. I look forward to hearing from Bay Area people! ------------------------------ Subject: Re: Neuron Digest V6 #66 From: landman@hanami.Eng.Sun.COM (Howard A. Landman) Organization: Sun Microsystems, Mt. View, Ca. Date: 20 Nov 90 01:30:34 +0000 >From: UAP001%DDOHRZ11.BITNET@CUNYVM.CUNY.EDU, >Date: Tue, 13 Nov 90 16:12:31 +0700 >Think of what (insert name of your favorite intellectual >hero here) did with the available circuits. >It could of course be argued that such exceptions had exceptional >hardware (although there's never been convincing anatomic or histologic >evidence for this). Anyone who's seen (or even read descriptions of) the brain of C.F.Gauss would have strong reason to disagree with this statement. Its cortex had about twice as many folds as that of a "normal" human brain. Howard A. Landman landman@eng.sun.com -or- sun!landman ------------------------------ Subject: call for papers for COLT '91 From: David Haussler <haussler@saturn.ucsc.edu> Date: Sun, 18 Nov 90 22:18:16 -0800 CALL FOR PAPERS COLT '91 Fourth Workshop on Computational Learning Theory Santa Cruz, CA. August 5-7, 1991 The fourth workshop on Computational Learning Theory will be held at the Santa Cruz Campus of the University of California. Registration is open, within the limits of the space available (about 150 people). In previous years COLT has focused primarily on developments in the analysis of learning algorithms within certain computational learning models. This year we would like to widen the scope of the workshop by encouraging papers in all areas that relate directly to the theory of machine learning, including artificial and biological neural networks, robotics, pattern recognition, information theory, decision theory, Bayesian/MDL estimation, and cryptography. We look forward to a lively, interdisciplinary meeting. As part of our program, we are pleased to present two special invited talks. "Gambling, Inference and Data Compression" Prof. Tom Cover of Stanford University "The Role of Learning in Autonomous Robots" Prof. Rodney Brooks of MIT Authors should submit an extended abstract that consists of: (1) A cover page with title, authors' names, (postal and e-mail) addresses, and a 200 word summary. (2) A body not longer than 10 pages in twelve-point font. Be sure to include a clear definition of the theoretical model used, an overview of the results, and some discussion of their significance, including comparison to other work. Proofs or proof sketches should be included in the technical section. Experimental results are welcome, but are expected to be supported by theoretical analysis. Authors should send 11 copies of their abstract to L.G. Valiant, COLT '91, Aiken Computing Laboratory, Harvard University, Cambridge, MA 02138. The deadline for receiving submissions is February 15, 1991. This deadline is FIRM. Authors will be notified by April 8; final camera-ready papers will be due May 22. The proceedings will be published by Morgan-Kaufmann. Each individual author will keep the copyright to his/her abstract, allowing subsequent journal submission of the full paper. Chair: Manfred Warmuth (UC Santa Cruz). Local arrangements chair: David Helmbold (UC Santa Cruz). Program committee: Leslie Valiant (Harvard, chair), Dana Angluin (Yale), Andrew Barron (U. Illinois), Eric Baum (NEC, Princeton), Tom Dietterich (Oregon State U.), Mark Fulk (U. Rochester), Alon Itai (Technion, Israel), Michael Kearns (Int. Comp. Sci. Inst., Berkeley), Ron Rivest (MIT), Naftali Tishby (Bell Labs, Murray Hill), Manfred Warmuth (UCSC). Hosting Institution: Department of Computer and Information Science, UC Santa Cruz. Papers that have appeared in journals or other conferences, or that are being submitted to other conferences are not appropriate for submission to COLT. Unlike previous years, this includes papers submitted to the IEEE Symposium on Foundations of Computer Science (FOCS). We no longer have a dual submission policy with FOCS. Note: this call is being distributed to THEORY-NET, ML-LIST, CONNECTIONISTS, Alife, NEWS.ANNOUNCE.CONFERENCES, COMP.THEORY, COMP.AI, COMP.AI.EDU, COMP.AI.NEURAL-NETS, and COMP.ROBOTICS. Please help us by forwarding it to colleagues who may be interested and posting it on any other relevant electronic networks. - ------- End of Forwarded Message ------------------------------ Subject: Postdoctoral Positions From: Jordan B Pollack <pollack@cis.ohio-state.edu> Date: Tue, 20 Nov 90 13:00:39 -0500 POSTDOCTORAL FELLOWS IN COGNITIVE SCIENCE The Ohio State University The Center for Cognitive Science at the Ohio State University has several openings for postdoctoral researchers. We will consider recent Ph.D.'s in all areas of Cognitive Science based on overall quality of research and commitment to interdisciplinary work. Applications are especially encouraged from candidates in areas in which we have active faculty interests.(See attached note) These two-year positions will begin July 1991 and carry a yearly stipend of $25,000 with $1000 for moving expenses and $1000 per year for research and travel. An office and computer access will be provided by the Center. The Center for Cognitive Science is an interdisciplinary University-wide research center with approximately eighty members from sixteen departments. OSU is one of the largest universities in the country with significant research resources including a Cray YMP and a PET scanner. Columbus provides a high quality of life along with very affordable housing. To apply, send your vita, reprints and a statement of research interests and a research plan, tell us the name of the faculty member(s) you wish to work with at OSU, and arrange for three recommendation letters to be sent to: Postdoctoral Search Commmittee Center for Cognitive Science 208 Ohio Stadium East 1961 Tuttle Park Place Columbus, OH 43210-1102 Materials must be postmarked by January 15, 1991. The Ohio State University is an Equal Opportunity/Affirmative Action employer. ------------------------------------- I've put a summary of the main interests of the center in neuroprose (file OSU.Cogsci). Personally, I am looking for someone with a solid background in non-linear dynamical systems to collaborate on the question of how fractals and chaos are exploited by cognition. Other opportunities exist in neuroscience, AI, vision, speech, language, music, motor control, philosophy of mind, and elsewhere, under sponsorship of faculty in those areas. Please contact me (and/or any other faculty you know at OSU) for further info. Jordan Pollack Assistant Professor CIS Dept/OSU Laboratory for AI Research 2036 Neil Ave Email: pollack@cis.ohio-state.edu Columbus, OH 43210 Fax/Phone: (614) 292-4890 ------------------------------ Subject: Copenhagen Optimization Conference From: WANG@nbivax.nbi.dk Date: Wed, 21 Nov 90 12:56:00 +0100 ------------------------------------------------------------ INTERNATIONAL CONFERENCE ON NOVEL METHODS IN OPTIMIZATION February 7 - 8, 1991 arranged by NORDITA Nordic Institute of Theoretical Physics Copenhagen and DIKU Department of Computer Science University of Copenhagen supported by funding from Nordic Initiative for Neural Computation (NINC) ------------------------------------------------------------ In recent years there has been an increasing interest in using neural networks, simulated annealing, and genetics as modelling frames of reference to construct novel search heuristics for solving hard optimization problems. Algorithms constructed in this way, together with tabu search, constitute promising new approaches to optimization and are the subjects of this conference. The aim of the conference is to bring together researchers in classical optimization and researchers working with the novel methods, thus enabling a fruitful exchange of information and results. An important part of the conference will be a tutorial presentation of both classical and new methods to establish a common base for discussion among the participants. Tutorial session. ----------------- The first day of the conference will be devoted to introductory lectures given by invited speakers. The lectures will be on: * Classical Optimization. a) Laurence Wolsey, Center for Operations Research and Econometrics, Universite de Louvain, Belgium: Introduction to Classical Optimization: P-problems and their solution. b) Susan Powell, London School of Economics: Introduction to Classical Optimization: NP-problems and their solution. * Neural Networks. Carsten Peterson, Lund University, Sweden: The use of neural networks and optimization. * Simulated Annealing. (Speaker to be announced later) * Genetic Algorithms. (Speaker to be announced later) * Tabu Search. (Speaker to be announced later) * Statistical Mechanics. Marc Mezard, Ecole Normale Superieure, Paris: "Formal statistical mechanical methods in optimization problems." About the speakers: Laurence A. Wolsey is Professor of Applied Mathematics at CORE and is one of the leading researchers in the field of computational mathematical programming. He received the Beale-Orchard-Hays prize for his work in 1988, and is one of the authors of the widely used book "Integer and Combinatorial Optimization". Susan Powell is Lecturer in Operations Research at London School of Economics and is well known for her work on Fortran Codes for linear and integer programs. She has a solid background in prac- tical problem solving through her contacts with industry and British OR companies. Carsten Peterson is Lecturer in Theoretical Physics at Lund University. He is co-inventor of the deterministic Boltzmann learning algorithm for symmetric recurrent networks and a leader in applications of neural networks to optimization problems. Marc Mezard is Lecturer in Physics at the Ecole Nomale Superieure, Paris. Together with his colleagues there and their coworkers at the University of Rome, he pioneered the application of methods from the statistical mechanics of random systems to optimizaation problems. Contributed Papers. ------------------- The second day of the conference will be devoted to selected half-hour contributed presentations. An abstract of each paper submitted for presentation should be mailed or e-mailed to: Prof. Jens Clausen DIKU, Dept. of Computer Science Universitetsparken 1, DK-2100 Copenhagen OE Denmark. e-mail: clausen@diku.dk before January 1, 1991. Authors of accepted papers will be notified before January 15, 1991. (No proceedings will be published). Poster Sessions. ---------------- On both seminar days there will be poster sessions. An abstract of the poster should be mailed or e-mailed to Prof. Jens Clausen DIKU, Dept. of Computer Science Universitetsparken 1, DK-2100 Copenhagen OE Denmark. e-mail: clausen@diku.dk before january 1, 1991. Authors of accepted posters will be notified before January 15, 1991. Registration. ------------- The registration fee is 500 DKK (or equivalent in other convertible currency) and covers coffee/tea and lunch both days as well as an informal conference dinner on the evening of February 7. To register please fill in the form below and mail it together with the registrations fee to the address given on the form. No credit cards accepted. Cheques or Eurocheques should be payable to OPTIMIZATION CONFERENCE. The organizing commitee must receive your registration form January 15, 1991 the latest, and the final program will be mailed by January 22, 1991. Travel support for Nordic participants. --------------------------------------- A limited amount of money from NINC is reserved for paying the travel costs of participants from the Nordic countries, especially younger researchers. If you would like to apply for this support, please indicate on the registration form. Accommodation. -------------- The organizing commitee has reserved a certain number of hotel rooms. Please indicate on the registration form if you would like the conference to book one for you. ------------------------------------------------------------- INTERNATIONAL CONFERENCE ON NOVEL METHODS IN OPTIMIZATION February 7 - 8, 1991 ------------------------------------------------------------- REGISTRATION FORM ------------------------------------------------------------- Name:_______________________________________________ Affiliation:_______________________________________________ Address:_______________________________________________ _______________________________________________ _______________________________________________ Telephone no.:_______________________________________________ e-mail:_______________________________________________ If you want the conference to reserve you a hotel room, please indicate here for which nights: ______________________________________________________________ Nordic participants: If you want to be considered for travel support, please indicate your needs here: ______________________________________________________________ Mail this registration form to: John Hertz NORDITA Blegdamsvej 17 DK-2100 Copenhagen OE, Denmark For further information: e-mail: hertz@nordita.dk FAX: [+45] 31 38 91 57 ------------------------------ End of Neuron Digest [Volume 6 Issue 68] ****************************************