neuron-request@HPLMS2.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") (03/17/90)
Neuron Digest Friday, 16 Mar 1990 Volume 6 : Issue 21 Today's Topics: re: Searle questions Re: Music by Kohonen's NN NN's and Music, and a Question (was Music by Kohonen's NN) Re: NN's and Music, and a Question (was Music by Kohonen's NN) Neural Networks application? Applications of Neural Nets in Image Processing and Biomedical Imaging Re^2: ARTS TR available - higher order recurrent networks POSTDOCTORAL POSITION IN COGNITIVE NEUROSCIENCE -- SAN DIEGO Australian neural networks conference, Feb 1991 NN Conference April 12-13-14 research position available International Journal of Neural Systems 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: Searle questions From: dank@moc.Jpl.Nasa.Gov (Dan Kegel) Date: Mon, 12 Mar 90 19:42:42 -0800 I suspect that Searle's Chinese Room claim is just a consequence of a more basic premise, which can be rephrased: "Mind you, I'm not saying that computers can't think. It's computers that are based on pure symbol manipulation that I claim cannot think. Specifically, they cannot think because they do not duplicate the causal powers of brains." Even a computer running an exact simulation of a brain does not satisfy him. As has been pointed out, it is possible in principle to graft biological sensory organs [aka causal powers] onto such a computer. Searle would, if pressed, probably admit that the resulting system could think and understand. After all, it has duplicated a brain's causal powers, hasn't it? {Can somebody supply Searle's address, so we can direct the question to him?} But are sensory inputs really needed for thought? Imagine disconnecting a brain's "causal powers" one by one. Does thinking cease when the nose is disconnected? No. When the eyes are shut? No. When the angiotensin receptors that mediate thirst are removed? No again; in fact, it seems reasonable that thought could continue when all sensory input is removed. The remaining causal power is memory, which I state is sufficient. Dan Kegel [[ Editor's Note: John Searle's address is searle@cogsci.berkeley.edu. -PM ]] ------------------------------ Subject: Re: Music by Kohonen's NN From: smoliar@vaxa.isi.edu (Stephen Smoliar) Organization: USC-Information Sciences Institute Date: 13 Mar 90 18:34:30 +0000 [[ From last issue: ]] >Kohonen's "Neural Network Music" actually is not Neural Network Music >(at least what he presented at IJCNN '90) He informed the audience >that it was based more on a stochastic analysis of human composers >(including mixing various composers). Readers more interested in what can be done with neural networks may wish to check out Peter Todd's contribution to the 1988 Connectionist Models Summer School. Todd is a psychologist, and he seems more concerned with modeling phenomena which have been observed in psychological experiments. I would say there is still some doubt as to how relevant those experiments are to music as it is actually practiced, but at least Todd appears to be approaching the problem more scientifically. ========================================================================= USPS: Stephen Smoliar USC Information Sciences Institute 4676 Admiralty Way Suite 1001 Marina del Rey, California 90292-6695 Internet: smoliar@vaxa.isi.edu "Only a schoolteacher innocent of how literature is made could have written such a line."--Gore Vidal ------------------------------ Subject: NN's and Music, and a Question (was Music by Kohonen's NN) From: robert@aerospace.aero.org (Bob Statsinger) Organization: Ahh...wouldntya like to know! Date: 14 Mar 90 18:51:22 +0000 The two most recent issues (vols 12 and 13) of "Computer Music Journal" are completely devoted to neural nets and connectionism as applied to musical composition and models of music perception. Todd has a GREAT article in vol 13 on a recurrent network he developed for algorithmic composition. There are also backpropagation models of pitch perception (Jenkins), bidirectional linear nets for inferring tonality (Bharucha), and in vol 12 an ART system for musical classification. This semester I am working on applying invariant object recognition to attempt to model the recognition of musical melody independent of key signature (invariance with respect to tempo and mild distortion invariance are also desirable). I have not seen this attempted anywhere in the literature that I've seen so far. If anyone has seen such an attempt, PLEASE respond in a followup posting and/or by e-mail. Thanx much. Bob Statsinger Robert@aerospace.aero.org The employers expressed herein are strictly mine and are not necessarily those of my opinion's....uh..er...whatever... ------------------------------ Subject: Re: NN's and Music, and a Question (was Music by Kohonen's NN) From: smoliar@vaxa.isi.edu (Stephen Smoliar) Organization: USC-Information Sciences Institute Date: 15 Mar 90 21:47:01 +0000 > The two most recent issues (vols 12 and 13) of "Computer Music >Journal" are completely devoted to neural nets and connectionism as >applied to musical composition and models of music perception. Thanks for coming to my rescue, Bob! I received two electronic mail requests for details but was tardy in responding due to being snowed under by two papers I'm trying to wrap up! Nevertheless, your citation had better get corrected before things get out of hand. The two issues are Numbers 3 and 4 of Volume 13 (not volumes 12 and 13). For those interested in the specific articles, the Jenkins piece on pitch perception and Gjerdingen's ART piece are in Number 3. Bharucha and Todd are in Number 4. Personally, I did not think very much about the ART article; but I am prepared to be persuaded otherwise. ========================================================================= USPS: Stephen Smoliar USC Information Sciences Institute 4676 Admiralty Way Suite 1001 Marina del Rey, California 90292-6695 Internet: smoliar@vaxa.isi.edu "Only a schoolteacher innocent of how literature is made could have written such a line."--Gore Vidal ------------------------------ Subject: Neural Networks application? From: Javier Tuya Gonzalez <Tuya@etsiig.uniovi.es> Date: 16 Mar 90 16:50:00 +0200 Has anybody information (people who works in, papers published, etc.) about some application of Neural Networks for: Classification of crystal structures using X-ray diffraction data Could be possible to apply Neural Networks for it? Please, post me E-mail if you can help me. Thanks in advance. +--------------------------------------+------------------------------------+ | Pablo Javier Tuya Gonzalez | PSI: PSI%(02145)285060338::TUYA | | E.T.S. Ingenieros Industriales | E-Mail: tuya@etsiig.uniovi.es | | Area de Lenguajes y Sistemas | HEPNET: tuya@16515.decnet.cern.ch | | Informaticos (Universidad de Oviedo) | : EASTVC::TUYA (16.131) | | Carretera de Castiello s/n. | Phone: (..34-85) 338380 ext 278 | | E-33394 GIJON/SPAIN | FAX: (..34-85) 338538 | +--------------------------------------+------------------------------------+ ------------------------------ Subject: Applications of Neural Nets in Image Processing and Biomedical Imaging From: m20163@mwvm.mitre.org (Nahum Gershon) Date: Fri, 16 Mar 90 09:52:10 -0500 I am looking for information on any work done on the use of neural nets in image processing and also in biomedical imaging. Any help would be greatly appreciated. Nahum Gershon The MITRE Corp. MS Z575 7525 Colshire Drive McLean, VA 22102 E-mail: gershon@mitre.org Phone: (703) 883-7518 Fax: (703) 883-7175 ------------------------------ Subject: Re^2: ARTS From: gaudiano@bucasb.bu.edu Date: Thu, 15 Mar 90 15:00:20 -0500 >>>> In reply to Jason Kingdon's message about the problem with ART1: Well, there are two ways to address you question: one answer is that, indeed, you have found one of the problems with ART1. This problem has to do with the fact that all top-down LTM traces are forced to 1 in fast learning (or asymptotically in slow learning), so that the top-down template match exceeds the critical strength regardless of the number of nonzero weights in the top-down LTM trace. This can in fact be avoided in ART2-3. The other answer: The ART1 architecture was designed so that templates can only shrink. This ensures that a maximal number of exemplars can be categorized, depending on the vigilance level. If a single node has non-zero strength, then at vigilance 1 you can only code the one-element vector, but as you drop vigilance you can code more and more patterns based on the "atomic" subpattern. So basically you have shown that this categorization network, when severely restricted in memory capacity, and when forced to make extremely fine discriminations (vigilance=1) will only become stable on the most *basic* pattern that can possibly grab a category (but can still code supersets at lower vigilance). Does this constitute an example of "rendering the system useless"? I would consider it a fascinating feature. Paolo Gaudiano ------------------------------ Subject: TR available - higher order recurrent networks From: "Giles L." <giles@fuzzy.nec.com> Date: Fri, 09 Mar 90 15:11:50 -0500 This 8-page paper will appear in Advances in Neural Information Processing Systems 2, D.S. Touretzky (ed), Morgan Kaufmann, San Mateo, Ca., 1990. HIGHER ORDER RECURRENT NETWORKS & GRAMMATICAL INFERENCE C. L. Giles*, G. Z. Sun, H. H. Chen, Y. C. Lee, D. Chen Department of Physics and Astronomy and Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742. *NEC Research Institute, 4 Independence Way, Princeton, N.J. 08540 ABSTRACT We design a higher-order single layer, recursive neural network which easily learns to simulate a deterministic finite state machine and infer simple regular grammars from small training sets. An enhanced version of this neural network state machine is then constructed and connected through a common error term to an external analog stack memory. The resulting hybrid machine can be interpreted as a type of neural net pushdown automata. The neural net finite state machine part is given the primitives, push and pop, and is able to read the top of the stack. Using a gradient descent learning rule derived from a common error function, the hybrid network learns to effectively use the stack actions to manipulate the stack memory and to learn simple context-free grammars. If the neural net pushdown automata are reduced through a heuristic clustering of neuron states and actions, the neural network reduces to correct pushdown automata which recognize the learned context-free grammars. For a hard copy of the above, please send a request to: gloria@research.nec.com or Gloria Behrens NEC Research Institute 4 Independence Way Princeton, N.J. 08540 ------------------------------ Subject: POSTDOCTORAL POSITION IN COGNITIVE NEUROSCIENCE -- SAN DIEGO From: trejo@nprdc.arpa (Leonard J. Trejo) Organization: Navy Personnel R & D Center Date: 13 Mar 90 22:42:49 +0000 POSTDOCTORAL POSITION IN COGNITIVE NEUROSCIENCE -- SUMMER/FALL 1990 The Neurosciences Division of the Navy Personnel Research and Development Center (NPRDC), San Diego, is looking for a recent Ph. D. to study electrophysiological correlates of human cognition. Ongoing research includes neuroelectric (EEG and ERP) and neuromagnetic (evoked field) technology. The primary emphasis is on the improvement of on-job performance prediction and training; however, considerable emphasis is given to basic research issues. Another area of interest is in real-time electrophysiological signal processing using adaptive filters and neural networks. The well-equipped Neuroscience Labora- tory includes two Concurrent computer systems, several '386 PC sys- tems, a Macintosh SE, and other equipment, as well as extensive stimulus presentation, data acquisition and analysis software. Access privileges to VAX 11/780, IBM 4341, and SUN 4 systems, and the INTER- NET network are also available. An associate investigator role will be assumed by the successful candidate and he/she will be expected to develop a line of research in concert with Center goals. Qualifications include: 1. U. S. Citizenship 2. Ph. D., Sc. D., or equivalent in psychology or neuroscience received not more than 7 years from date of award Additional experience desired: 1. Cognitive psychophysiology training / experience 2. Experimental design / methodology 3. Multivariate / univariate statistics 4. Proficiency with UNIX and C programming The position is available through the Postdoctoral Fellowship Program funded by the U.S. Navy Office of Naval Technology (ONT) and administered by the American Society for Engineering Education (ASEE). Duration of the appointment is for one year, and may be renewed for up to two additional years. Stipends range from $34,000 to $38,000 per annum depending upon experience. A relocation allowance may be nego- tiated; the amount is based on the personal situation of the partici- pant. Funds will be available for limited professional travel. NPRDC is located on top of Pt. Loma, overlooking San Diego Harbor and downtown San Diego. Reasonably priced rental housing is available in within a 5-mile radius of the Center. San Diego offers an excel- lent climate and environment as well as a wide range of academic, mil- itary, and industrial research institutions. The application deadlines are April 1, 1990, for terms beginning in the summer, and July 1, 1990, for terms beginning in the fall. For information about the ONT Postdoctoral Fellowship Program and an application form, please contact: American Society for Engineering Education Projects Office, Attention: Bob Davis 11 Dupont Circle, Suite 200 Washington, DC 20036 (202) 293-7080 For information about the NPRDC Neurosciences Division, contact: Dr. Leonard J. Trejo Neuroscience Division, Code 141 Navy Personnel Research and Development Center San Diego, CA 92152-6800 (619) 553-7711 INTERNET: trejo@nprdc.navy.mil UUCP: ucsd!nprdc!trejo ============================================================================ USENET : trejo@nprdc.navy.mil UUCP: ucsd!nprdc!trejo U.S. Mail: Leonard J. Trejo, Ph. D. Phone: (619) 553-7711 Neurosciences Division (AV) 553-7711 NPRDC, Code 141 San Diego, CA 92152-6800 ------------------------------ Subject: Australian neural networks conference, Feb 1991 From: Janet Wiles <janet@psych.psy.uq.OZ.AU> Date: Wed, 14 Mar 90 16:56:21 +1100 PRELIMINARY ANNOUNCEMENT SECOND AUSTRALIAN CONFERENCE ON NEURAL NETWORKS (ACNN'91) 4th - 6th February 1991 THE UNIVERSITY OF SYDNEY SYDNEY, AUSTRALIA The second Australian conference on neural networks will be held in Sydney on Feb 4, 5 and 6, 1991, at the Stephen Roberts Theatre, The University of Sydney. This conference is interdisciplinary, with emphasis on cross discipline communication between Neuroscientists, Engineers, Computer Scientists, Mathematicians and Psychologists concerned with understanding the integrative nature of the nervous system and its implementation in hardware/software. Neuroscientists concerned with understanding the integrative function of neural networks in vision, audition, motor, somatosensory and autonomic functions are invited to participate and learn how modelling these systems can be used to sharpen the design of experiments as well as to interpret data. Mathematicians and computer scientists concerned with the various new neural network algorithms that have recently become available, as well as with statistical thermodynamic approaches to network modelling and simulation are also invited to contribute. Engineers concerned with the advantages which parallel and distributed computing architectures offer in the solution of various classes of problems and with the state of the art techniques in the hardware implementation of neural network systems are also invited to participate. Psychologists interested in computational models of cognition and perception are invited to contribute and to learn about neural network techniques and their biological and hardware implementations. ACNN'91 will feature invited keynote speakers in the areas of neuroscience, learning, modelling and implementations. The program will include pre-conference workshops, presentations and poster sessions. Proceedings will be printed and distributed to the attendees. Expression of Interest: ----------------------- Please fill the expression of interest form below and return it to Miss Justine Doherty at the address below. ___ I wish to attend the conference ___ I wish to attend the workshops ___ I wish to present a paper Title: _____________________________________________________ _____________________________________________________ Authors: ___________________________________________________ _____________________________________________________ ___ I wish to be on your mailing list My areas of interests are: ____ Neuroscience ____ Learning ____ Modelling ____ Implementation ____ Applications ____ Other: _______________________________________ First Name: ___________________________ Surname: ______________________________ Title: ________________________________ Position:______________________________ Department: ___________________________________________________________ Institution:___________________________________________________________ Address:_______________________________________________________________ _______________________________________________________________________ City: _______________________________ State: __________________________ Zip Code: _________________________ Country: __________________________ Tel: ______________________________ Fax: ______________________________ Email: _________________________________________ ________________________________________________________________________ Organising committee: Chairman Dr Marwan Jabri, Sydney Co-chairman Professor Max Bennett, Sydney Technical Program Chairman Dr Ah Chung Tsoi, ADFA Technical Program Co-Chairman Professor Bill Levick, ANU Publicity Dr Janet Wiles, Queensland Registration Electrical Engineering Foundation Conference Committee Professor Yanni Attikiousel, WA Professor Max Bennett, Sydney Professor Bob Bogner, Adelaide Professor Richard Brent, ANU Dr Jacob Cybulski, TRL Dr Marwan Jabri, Sydney Professor Bill Levick, ANU Dr Tom Osbourn, UTS Professor Steve Redman, ANU Ass/Prof Sam Reisenfeld, OTC Ltd Professor Graham Rigby, UNSW Professor Steve Schwartz, Queensland Dr Ah Chung Tsoi, ADFA Dr Charles Watson, DSTO Dr Janet Wiles, Queensland Dr Hong Yan, Sydney For further information contact: Miss Justine Doherty Secretariat ACNN'91 Sydney University Electrical Engineering NSW 2006 Australia Tel: (+61-2) 692 3659 Fax: (+61-2) 692 3847 Email: acnn91@ee.su.oz.au _____________________________________________________________________________ ------------------------------ Subject: NN Conference April 12-13-14 From: Samir Sayegh <sayegh@ed.ecn.purdue.edu> Date: Thu, 15 Mar 90 17:41:16 -0500 Third Conference on Neural Networks and PDP (Robotics and Vision) Indiana-Purdue University Deadline for submission of a 1 page abstract is March 23. e-mail and FAX submissions OK. Conference fee is $25. Students attend free. Inquiries and abstracts: S.Sayegh Physics Dept. Indiana Purdue University Ft Wayne In 46805 email: sayegh@ed.ecn.purdue.edu sayegh@ipfwcvax.bitnet fax: (219) 481-6800 voice:(219)481-6157 ------------------------------ Subject: research position available From: "James A. Reggia" <reggia@cs.UMD.EDU> Date: Thu, 15 Mar 90 20:22:20 -0500 RESEARCH SCIENTIST POSITION AVAILABLE IN NEURAL MODELLING The component of The Food and Drug Administration responsible for regulating medical devices has an opening for a research scientist. This is a permanent civil service position available for someone interested in modelling the neural activity of the hippocampus. The candidate will focus his/her research on improving the safety and effectiveness of electro-convulsive therapy devices. The candidate must have a PhD in one of the physical sciences. Any additional training in the biological sciences is highly desirable. For more information call or write to: Dr. C. L. Christman (301) 443-3840 Address: FDA HFZ-133 12721 Twinbrook Pkwy Rockville, MD 20857 (Do NOT send inquiries for further information via email to the individual posting this announcement.) ------------------------------ Subject: International Journal of Neural Systems From: Benny Lautrup <LAUTRUP%nbivax.nbi.dk@CUNYVM.CUNY.EDU> Date: Fri, 16 Mar 90 12:28:00 +0100 INTERNATIONAL JOURNAL OF NEURAL SYSTEMS The International Journal of Neural Systems is a quarterly journal which covers information processing in natural and artificial neural systems. It publishes original contributions on all aspects of this broad subject which involves physics, biology, psychology, computer science and engineering. Contributions include research papers, reviews and short communications. The journal presents a fresh undogmatic attitude towards this multidisciplinary field with the aim to be a forum for novel ideas and improved understanding of collective and cooperative phenomena with computational capabilities. ISSN: 0129-0657 (IJNS) - ---------------------------------- Contents of issue 1: 1. C. Peterson and B. Soderberg: A new Method for mapping Optimization Problems onto Neural Networks. 2. M. G. Paulin, M. E. Nelson and J. M. Bower: Dynamics of Compensatory Eye Movement Control: An Optimal Estimation Analysis of the Vestibulo-Ocular Reflex. 3. P. Peretto: Learning Learning Sets in Neural Networks. 4. B. A. Huberman: The Collective Brain. 5. S. Patarnello and P. Carnevali: A Neural Network Model to Simulate a conditioning Experiment. 6. J.-P. Nadal: Study of a Growth Algorithm for a Feed-Forward Network. 7. E. Oja: Neural Networks, Principal Components and Subspaces. 8. S. Bacci, G. Mato, and N. Parga: The Organization of Metastable States in a Neural Network with Hierarchical Patterns. 9. A. Lansner and O. Ekeberg: A One-layer Feedback Artificial Neural Network with a Bayesian Learning Rule. 10. J. Midtgaard and J. Hounsgaard: Nerve Cells as Source of Time Scale and Processing Density in Brain Function. 11. S. Chen: On Computational Vision. - ---------------------------------- Contents of issue 2: 1. P. Baldi and A. Attiya: Oscillations and synchronizations in neural networks: An exploration of the labeling hypothesis. 2. A. W. Smith and D. Zipser: Learning sequential structure with the real-time recurrent learning algorithm. 3. M. R. Davenport and G. W. Hoffmann: A recurrent neural network using tri-state hidden neurons to orthogonalize the memory space. 4. H. K. M. Yusuf, S. Rahman and H. Akhtar: Rats kept in environmental isolation for twelve months from weaning: Performance in maze learning and visual discrimination tasks and brain composition. 5. H. C. Card and W. R. Moore: VLSI devices and circuits for learning in neural networks. 6. L. Gislen, C. Peterson and B. Soderberg: "Teachers and classes" with neural networks. 7. A. E. Gunhan, L. P. Csernai, and J. Randrup: Unsupervised competitive learning in Purkinje networks. 8. H.-U. Bauer and T. Geisel: Motion detection and direction detection in local neural nets. - ---------------------------------- Editorial board: B. Lautrup (Niels Bohr Institute, Denmark) (Editor-in-charge) S. Brunak (Technical Univ. of Denmark) (Assistant Editor-in-Charge) D. Stork (Stanford) (Book review editor) Associate editors: B. Baird (Berkeley) D. Ballard (University of Rochester) E. Baum (NEC Research Institute) S. Bjornsson (University of Iceland) J. M. Bower (CalTech) S. S. Chen (University of North Carolina) R. Eckmiller (University of Dusseldorf) J. L. Elman (University of San Diego) M. V. Feigelman (Landau Institute for Theoretical Physics) F. Fogelman-Soulie (Paris) K. Fukushima (Osaka University) A. Gjedde (Montreal Neurological Institute) S. Grillner (Nobel Institute for Neurophysiology, Stockholm) T. Gulliksen (University of Oslo) D. Hammerstroem (University of Oregon) J. Hounsgaard (University of Copenhagen) B. A. Huberman (XEROX PARC) L. B. Ioffe (Landau Institute for Theoretical Physics) P. I. M. Johannesma (Katholieke Univ. Nijmegen) M. Jordan (MIT) G. Josin (Neural Systems Inc.) I. Kanter (Princeton University) J. H. Kaas (Vanderbilt University) A. Lansner (Royal Institute of Technology, Stockholm) A. Lapedes (Los Alamos) B. McWhinney (Carnegie-Mellon University) M. Mezard (Ecole Normale Superieure, Paris) A. F. Murray (University of Edinburgh) J. P. Nadal (Ecole Normale Superieure, Paris) E. Oja (Lappeenranta University of Technology, Finland) N. Parga (Centro Atomico Bariloche, Argentina) S. Patarnello (IBM ECSEC, Italy) P. Peretto (Centre d'Etudes Nucleaires de Grenoble) C. Peterson (University of Lund) K. Plunkett (University of Aarhus) S. A. Solla (AT&T Bell Labs) M. A. Virasoro (University of Rome) D. J. Wallace (University of Edinburgh) D. Zipser (University of California, San Diego) - ---------------------------------- CALL FOR PAPERS Original contributions consistent with the scope of the journal are welcome. Complete instructions as well as sample copies and subscription information are available from The Editorial Secretariat, IJNS World Scientific Publishing Co. Pte. Ltd. 73, Lynton Mead, Totteridge London N20 8DH ENGLAND Telephone: (44)1-446-2461 or World Scientific Publishing Co. Inc. 687 Hardwell St. Teaneck New Jersey 07666 USA Telephone: (1)201-837-8858 or World Scientific Publishing Co. Pte. Ltd. Farrer Road, P. O. Box 128 SINGAPORE 9128 Telephone (65)278-6188 ------------------------------ End of Neuron Digest [Volume 6 Issue 21] ****************************************