Path: utzoo!attcan!uunet!cs.utexas.edu!usc!apple!bionet!agate!ucbvax!HPLMS2.HPL.HP.COM!neuron-request From: neuron-request@HPLMS2.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") Newsgroups: comp.ai.neural-nets Subject: Neuron Digest V6 #64 Message-ID: <25259.657919188@hplpm.hpl.hp.com> Date: 6 Nov 90 19:19:48 GMT Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: "Neuron-Request" Organization: Hewlett-Packard Laboratories Lines: 738 Neuron Digest Tuesday, 6 Nov 1990 Volume 6 : Issue 64 Today's Topics: NN texts: a summary. PRE-PRINT AVAILABILITY. Request for a paper in Cognitive Neuroscience. NIPS demo machines Book prices Haptic displays? Universities offering programs in Cognitive Science A question POSITION IN COGNITIVE PSYCHOLOGY, MCGILL UNIVERSITY CNS Program at Boston University Hiring 2 Assistant Professors _homo_trans sapiens, request for comments Neural Computer Seminar Cog Sci One-Day Conference (Rutgers) paper available Technical Report CSRP162 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: NN texts: a summary. From: Robert Elliott Smith Date: Thu, 25 Oct 90 16:43:20 -0500 [[ Editor's Note: The subject of "introductory texts" or "survey texts" comes up very often. Many of you readers have purchased the books listed below as well as others in the myriad available. I'm sure Rob (as well as I and othre readers) would like to hear what YOU think of the books you have read and or used for classes. For example, are the Rumelhart and McClelland PDP books now too "out of date"? I suspect not, but want to hear what YOU have to say... -PM ]] Dear Connectionists, A week ago I posted a message requesting recomendations for possible texts for a introductory, graduate level engineering course neural nets. I received some interesting responses (thanks), so I decided to summarize to the net. I'll keep my editorializing to a minimum, since I have not seen any of these texts yet. If you want to comparison shop, you'll have to do like me and call the publishers. The following texts were recomended: Neurocomputing by Robert Hecht-Nielsen Addison-Wesley Publishing Company 1990 (this received the most recomendations by far) (a solution manual is rumoured to be available soon.) Neural Networks in Artificial Intelligence by Matthew Zeidenberg Ellis Horwood Ltd., distributed in the US by Simon and Schuster (sounded awfully interesting) Introduction to Neural and Cognitive Modeling by Daniel S. Levine Lawrence Erlbaum Associates (not available yet) Adaptive Pattern Recognition and Neural Networks by Y. Pao (no detailed bib entry, sorry) Neurocomputing (??) by Wasserman (no detailed bib entry, sorry) Artificial Neural Systems by Patrick Simpson Pergamon Press That's it. I hope some of you find this helpful. Sincerely, Rob ------------------------------------------- Robert Elliott Smith Department of Engineering of Mechanics The University of Alabama P. O. Box 870278 Tuscaloosa, Alabama 35487 <> rob@galab2.mh.ua.edu <> (205) 348-4661 ------------------------------------------- ------------------------------ Subject: PRE-PRINT AVAILABILITY. From: P.Refenes@cs.ucl.ac.uk Date: Mon, 29 Oct 90 17:38:38 +0000 The following pre-print (SPIE-90, Boston, Nov. 5-9 1990) is available. (write or e-mail to A. N. Refenes at UCL) AN INTEGRATED NEURAL NETWORK SYSTEM for HISTOLOGICAL IMAGE UNDERSTANDING A. N. REFENES, N. JAIN & M. M. ALSULAIMAN Department of Computer Science, University College London, Gower Street, WC1, 6BT, London, UK. ABSTRACT This paper describes a neural network system whose architecture was designed so that it enables the integration of heterogeneous sub-networks for performing specialised tasks. Two types of networks are integrated: a) a low-level feature extraction network for sub-symbolic computation, and b) a high-level network for decision support. The paper describes a non trivial application from histopathology, and its implementation using the Integrated Neural Network System. We show that with careful network design, the backpropagation learning procedure is an effective way of training neural networks for histological image understanding. We evaluate the use of symmetric and asymmetric squashing functions in the learning procedure and show that symmetric functions yield faster convergence and 100% generalisation performance. ------------------------------ Subject: Request for a paper in Cognitive Neuroscience. From: anand@elsa.top.cis.syr.edu (Rangachari Anand) Organization: CIS Dept., Syracuse University Date: 30 Oct 90 16:42:30 +0000 I am searching for a paper by J. G. Rueckl, K. R. Caove and S. M. Kosslyn called 'Why are "what" and "where" processed by separate cortical visual systems? A computational investigation'. This paper was published in the Journal of Cognitve Neuroscience in 1989. If anyone has a copy of this paper could you please contact me by e-mail? Our library here unfortunately has not yet started subscribing to this journal. R. Anand Internet: anand@top.cis.syr.edu Bitnet: ranand@sunrise ------------------------------ Subject: NIPS demo machines From: Jim Bower Date: Wed, 31 Oct 90 08:13:52 -0800 Announcement NIPS Demo Machines Two machines will likely be available for demos at this year's NIPS meeting: 1 DECstation 5000/200PX with TK50 tape drive running Ultrix 4.0 1 Sparcstation 1+ or better RISC box from Sun with a 1/4" tape drive. running Sun OS 4.1c Both machines will be 8 bit depth color, have between 8 and 16Mb of memory. Participants should feel free to bring software demos. The machines are not, however, intended to be used to sell software. Machines will be schedualed on a first come first serve basis. Anyone with questions can contact John Uhley at uhley.smaug.cns.caltech.edu. John will also be available at the meeting. Jim Bower ------------------------------ Subject: Book prices From: Oscar Firschein Date: Wed, 31 Oct 90 14:57:19 -0800 I find neuron digest very useful. A suggestion: Include price as part of the new books announcements. [[Editor's Note: Book publishers and authors, take note! -PM ]] ------------------------------ Subject: Haptic displays? From: "Rustom Kersasp Vachha" Date: Thu, 01 Nov 90 10:21:32 -0800 I would like to send the following question on the network. Q. Has anybody tried to use HAPTIC displays (displays that affect the haptic senses- like feeling(touch)) inorder to train the neural network ? I am interested in pursuing it further. Can Neural networks be trained MANUALLY if the user experiences a force proportional to the error in the output and the exmplar assuming a suitable interface? This could help us understand the network better. An application of haptic displays for molecular docking is used by researchers at the UNIVERSITY OF NORTH CAROLINA, using the Argonne Remote Manipulator interface. Thankyou . Rustom ------------------------------ Subject: Universities offering programs in Cognitive Science From: mpaolini%sdcc13@ucsd.edu (Monica Paolini) Date: Sat, 03 Nov 90 18:20:06 -0800 I have just been offered a Fulbright scholarship for starting a PhD in Cognitive Science in the US and I am looking for a list of Universities where I could apply (I am interested in connectionist models for knowledge representation). Could you please provide me with some information about Universities offering programs in Cognitive Science? Personal comments/suggestions are warmly welcomed. Monica Paolini mpaolini%sdcc13@ucsd.edu [[ Editor's Note: Congrats to Monica. I've been doing a bit of searching for myself; I hope to matriculate in some program for fall 1991. I've discovered the range of "Cognitive Science" programs depends greatly on what your specific interests are (as one might expect). Cog Sci programs with a strong linguistic component seem to be dominant, while those which attempt to be more closely tied to biology or neurobiology are rarer. I'll try to dig up a summary from last year which was compiled by someone else. Being a bit more specific about what you want to do or study will help narrow the choices, especially if your interests lie in a dpeartment which may not be called "Cognitive Science". -PM ]] ------------------------------ Subject: A question From: qian@icopen.ICO.OLIVETTI.COM (DA QUN QIAN) Date: Mon, 05 Nov 90 10:47:59 +0100 Who could tell me the difference between neural nets and connectionist models? is there any definition of the connectionist model? Thanks in advance. Qian Daqun qian@icopen.ioc.olivetti.com [[ Editor's Note; Good question. To my mind, there is no diference really. One might argue that connectionist models are theoretic models of cognitive processes (to be contratsed with information processing boxology) which are implemented in the engineering neural net models, but I think this is drawing a silly line in shifting sands. -PM ]] ------------------------------ Subject: POSITION IN COGNITIVE PSYCHOLOGY, MCGILL UNIVERSITY From: Tony Marley Date: Fri, 26 Oct 90 14:31:16 -0500 Although Prof. Bregman is in charge of the search for someone to fill a position in COGNITIVE PSYCHOLOGY in the Department of Psychology at McGill University, I encourage mathematically and/or computationally oriented researchers to keep me informed of their interest. Although it is unlikelty that we will hire a "straight" mathematical or computational person for this position, I will certainly push for someone with mathematical and computational skills. In particular, I would very much like to see applicants in the general area of neural modeling. Please let me know if you apply, and feel free to contact me for further information. Tony Marley Professor, Department of Psychology Director, McGill Cognitive Science Centre email: INAM@MUSICB.MCGILL.CA Tel: 514-398-6128 (office) 514-488-2067 (home) ------------------------------------------------------------------ October 4, 1990 The Department of Psychology at McGill University plans to make a tenure-track appointment of an assistant or associate professor in COGNITIVE PSYCHOLOGY. The appointment will begin in September 1991, subject to the availability of funding. The department has a strong tradition in cognitive psychology and is affiliated with the Cognitive Science Centre at the university. It is strongly supportive of younger staff and tends to promote from within the department. We are looking for an outstanding researcher. Nevertheless, we place a great stress on our teaching program and are looking for a candidate that could make a special contribution to it. The applicant's research could be concerned with any aspect of cognitive psychology, broadly interpreted. The major criterion will be the excellence of the applicant. Please bring this letter to the attention of any individuals you think might be qualified to apply or to persons who might know of such individuals. Selection will begin in mid-January, 1991. Applicants should arrange for at least three confidential letters of support to be sent to the address below. They should also send a curriculum vitae, copies of research publications and a brief statement describing their teaching and research to: A.S. Bregman, Telephone: (514) 398-6103 Cognitive Search Committee FAX: (514) 398-4896 Department of Psychology, McGill University, E-mail: in09@musicb.mcgill.ca 1205 Dr. Penfield Avenue, or: in09@mcgillb.bitnet Montreal, Quebec, CANADA H3A lBl ------------------------------ Subject: CNS Program at Boston University Hiring 2 Assistant Professors From: mike@park.bu.edu Date: Tue, 30 Oct 90 14:43:52 -0500 Boston University seeks two tenure track assistant or associate professors starting in Fall, 1991 for its M.A. and Ph.D. Program in Cognitive and Neural Systems. This program offers an intergrated curriculum offering the full range of psychological, neurobiological, and computational concepts, models, and methods in the broad field variously called neural networks, connectionism, parallel distributed processing, and biological information processing, in which Boston University is a leader. Candidates should have extensive analytic or computational research experience in modelling a broad range of nonlinear neural networks, especially in one or more of the areas: vision and image processing, speech and language processing, adaptive pattern recognition, cognitive information processing, and adaptive sensory-motor control Candidates for associate professor should have an international reputation in neural network modelling. Send a complete curriculum vitae and three letters of recommendation to Search Committee, Cognitive and Neural Systems Program, Room 240, 111 Cummington Street, Boston University, Boston, MA 02215, preferably by November 15, 1990 but no later than January 1, 1991. Boston University is an Equal Opportunity/Affirmative Action employer. Boston University (617-353-7857) Email: mike@bucasb.bu.edu Smail: Michael Cohen 111 Cummington Street, RM 242 Center for Adaptive Systems Boston, Mass 02215 Boston University ------------------------------ Subject: _homo_trans sapiens, request for comments From: Elan Moritz Date: Sat, 03 Nov 90 18:46:55 -0800 [[ Editor's Note: This is a bit off the general subjec of this Digest, but could be an interesting diversion for readers who are a bit adventerous. -PM ]] TRANS_SAPIENS and TRANS_CULTURE *** REQUEST FOR COMMENTS ------------------------------------- In an earlier paper [Memetic Science: I - General Introduction; Journal of Ideas, Vol. 1, #1, 3-22, 1990] I postulated the emergence of a descendent of homo sapiens. This descendent will be primarily differentiated from h. sapiens by having * substantially greater cognitive abilities *. [the relevant section of the paper is included below]. >>>>> I plan to write a more substantive paper on the topic and would appreciate comments, speculation, arguments for & against this hypothesis. Relevant comments / arguments will be addressed in the paper and be properly acknowledged/referenced <<<<<. Elan Moritz <<<< -- text of h. trans sapiens section follows -- We also introduce here the concepts of trans-culture and Homo trans-sapiens (or simply trans-sapiens). While being topics of a future paper, trans-culture can be described as the next step of culture dominated by deep connections, interactions, and relationships between objects created by large human/machine teams. A manifest property of trans-culture is the extreme and transcendent complexity of interactions and relations between humans and the cultural objects involved, with the additional property of being non-accessible to Homo sapiens. Examples of trans-cultural objects already exist; for example, there is no individual who (at any given temporal instance) is an expert in all aspects of medicine, or who is familiar with all biological species and their relationships, or is an expert in all aspects of physics, or who is totally familiar with all aspects of even a single cultural artifact (e.g. Hubble space telescope, Space Shuttle design, or the total design of a nuclear power plant). In fact, we are approaching the point that certain proofs of mathematical theorems are becoming too long and difficult for any one individual to keep in conscious awareness. In a way, these transcendent and extended complexity relationships are examples of more complicated 'meta-memes', which is one of the reasons it is interesting to study the evolution of ideas. Homo trans-sapiens is the [postulated] next step in evolution of homo sapiens. There is no reason to expect or require that Homo sapiens will not undergo further evolution. The bio-historical trend indicates that the major evolutionary development in Homo is in the cortico-neural arena (i.e. increasingly more complex organization of the nervous system and the brain). Specifically it is the higher level cognitive - Knowledge Information Processing functions that set H. Sapiens apart. It is asserted here (and to be discussed in a future paper) that H. trans-sapiens is a logical consequence of evolution, and that the milieu and adaptive epigenetic landscape for H. trans-sapiens is already present in the form of trans-culture. It is indeed possible that the basic mutations are in place and trans-sapiens already exists or will appear in the biologically-near time frame. [ Please pass to other relevant news groups/ e-lists] Elan Moritz, snail mail: Elan Moritz The Institute for Memetic Research PO Box 16327, Panama City, Florida 32406 e mail: moritz@well.sf.ca.us [internet] ------------------------------ Subject: Neural Computer Seminar From: "Nick_Sheridon.PARC"@Xerox.COM Date: Thu, 25 Oct 90 10:01:57 -0700 [[ Editor's Note: Yes, this was last week, but I'm sending it off so you can read about what is happening. Unfortunately, I generally cannot get submissions out in one day's turnaround. As usual, if you have a submission which is time urgent, mark it as such and I'll do my best. Meanwhile, I hope the talk went well... -PM ]] Importance: high My first message was apparently restricted to Viewpoint users. Sorry. SPECIAL SEMINAR BITMAP GRAPHICS AND NEURAL NETWORKS CARY CORNFELD NEC RESEARCH INSTITUTE PRINCETON, NEW JERSEY FRIDAY, OCTOBER 26 2:00 P.M. AUDITORIUM ABSTRACT It has only been within the last few years that Bitmap Graphics has emerged from the realm of research oriented workstations to become the dominant paradigm used in commercial computer systems. As many of us know, beneath the simplicity of this display organization lies considerable complexity and sophisticated engineering. PARC's pioneering work in this area has enabled us to apply our basic understanding of these systems to other areas of computer design. The Optically Programmed Neural Computer described in this talk derives much of its heritage from bitmap graphics. The innovative element within this computer is an array of 14,400 amorphous silicon, photoconductive synapses. This array is remarkably similar to an active matrix flat display. The resulting neuro-computer is perhaps the largest ever built and is the first to offer dynamically programmable synapses with full analog depth. The machine has a rich, graphical user interface for monitoring and controlling its operation. A short video tape of its operation will be shown. Host: Nick Sheridon ------------------------------ Subject: Cog Sci One-Day Conference (Rutgers) From: leyton@cogsci-1.rutgers.edu (Michael Leyton) Date: Wed, 31 Oct 90 06:40:25 -0500 ---------------------------------------------------- COLUMBIA/PRINCETON/RUTGERS Cognitive Science Third One-Day Conference Nov 9th, 1990 ---------------------------------------------------- Robert Remez: A Botany of Perceptual Approaches (11-12) to Speech. Georges Rey: Content and Percepts. (12:30-1:30) Lynn Cooper: Probing the Nature of the (3-4) Mental Representation of Visual objects. Zenon Pylyshyn: Individuating and Indexing (4.30-5.30) Primitive Visual Features: Or; The Deixes we see with. Gil Harman and Steve Stich will chair the sessions. ----------------------------------------------------- Place-Time: Schermerhorn 614, Columbia, 11am-6pm Following the conference, there will be a reception with light refreshments at Lynn Cooper's apartment. ------------------------------------------------------ Conference organizers: Lynn Cooper, Gilbert Harman, Barbara Landau, Michael Leyton, Nancy Nersessian, Steve Stich. If you have suggestions concerning subsequent conferences, contact Michael Leyton at leyton@cogsci-1.rutgers.edu ------------------------------ Subject: paper available From: stefano nolfi Date: Mon, 29 Oct 90 12:19:36 -0400 The following technical report is now available. You can get it from: STIVA AT IRMKANT.BITNET. Send your real adress. RECALL OF SEQUENCES OF ITEMS BY A NEURAL NETWORK Stefano Nolfi* Domenico Parisi* Giuseppe Vallar** Cristina Burani* *Inst. of Psychology - C.N.R. - Rome **University of Milan - Italy ABSTRACT A network architecture of the forward type but with additional 'memory' units that store the hidden units activation at time 1 and re-input this activation to the hidden units at time 2 (Jordan, 1986; Elman, 1990) is used to train a network to free recall sequences of items. The network's performance exhibits some features that are also observed in humans, such as decreasing recall with increasing sequence length and better recall of the first and the last items compared with middle items. An analysis of the network's behavior during sequence presentation can ex- plain these results. INTRODUCTION Human beings possess the ability to recall a set of items that are presented to them in a sequence. The overall capacity of the memory systems used in this task is limited and the probability of recall decreases with increasing sequence length. A second relevant feature of human performance in this task is that the last (recency effect) and the initial (primacy effect) items of the sequence tend to be recalled better than the middle items. These serial position effects have been observed both in a free recall condition, in which subjects may recall the stimuli in any order they wish, and in a serial recall condition, in which subjects must preserve the presentation order. (See reviews concerning free and serial recall of sequences and the recency ef- fect in: Glanzer, 1972; Crowder, 1976; Baddeley and Hitch, 1977; Shallice and Vallar, 1990). In this paper we report the results of a simulation experiment in which we trained neural networks to recall sequences of items. Our purpose was to explore if a particular network architecture could function as a memory store for generating free recall of sequences of items. Furthermore, we wanted to determine if the recall performances of our networks exhibited the two features of human free recall that we have mentioned, that is, decreasing probability of recall with increasing sequence length and an U-shaped recall curve (for related works see: Schneider and Detweiler, 1987; Schreter and Pfeifer, 1989; Schweickert, Guentert and Hersberger, 1989). To appear in: In D.S.Touretzky, J.L. Elman, T.J. Sejnowski and G.E. Hinton (eds.), Proceedings of the 1990 Connectionist Models Summer School. San Matteo, CA: Morgan Kaufmann. REFERENCES Baddeley A.D., Hitch G.J. (1974). Recency re-examined. In S. Dornic (Ed.). Attention and performance (Vol. 6). Hillsdale, NJ:Erlbaum, pp. 647-667. Crowder R.G. (1976). Principles of learning and memory. Hillsdale, NJ: Erlbaum. Glanzer M. (1972). Storage mechanisms in recall. In G.H. Bower (Ed.). The Psychology of learning and motivation. Advances in research and theory. (Vol. 5). New York: Academic Press, pp. 129-193. Elman, J.L. Finding structure in time. (1990). Cognitive Science, 14, 179-211. Jordan, M.I. (1986). Serial order: A parallel distributed processing approach. Institute for Cognitive Science. Report 8604. University of California, San Diego. Shallice T., Vallar G. (1990). The impairment of auditory-verbal short-term storage. In: G. Vallar and T. Shallice (Eds.). Neuropsychological impairments of short-term memory. New York: Cambridge University Press, pp.11-53. Schneider, W., & Detweiler, M. (1987). A connectionist control architecture for working memory. In G.H. Bower (Ed.) The Psychology of learning and motivation vol 21. New York: Academic Press. Schreter, Z., & Pfeirer, R. (1989). Short term memory and long term memory interactions in connectionist simulations of psychological experiments on list learning. In L. Personnaz and G. Dreyfus (Eds.), Neural Network: From models to applications. Paris: I.D.S.E.T. Schweickert, R., Guentert, L., & Hersberger, L. (1989). Neural Network Models of Memory Span. Preceedings of the Eleventh Annual Conference of the Cognitive Science Society. Ann Arbor, Michigan. ------------------------------ Subject: Technical Report CSRP162 From: David Cliff Date: Fri, 02 Nov 90 15:01:55 +0000 The following report is now available: "Computational Neuroethology: A Provisional Manifesto" Dave Cliff, University of Sussex School of Cognitive and Computing Sciences CSRP162, May 1990. \begin{abstract} This paper questions approaches to computational modelling of neural mechanisms underlying behaviour. It examines ``simplifying'' (connectionist) models used in computational neuroscience and concludes that, unless embedded within a sensorimotor system, they are meaningless. The implication is that future models should be situated within closed-environment simulation systems: output of the simulated nervous system is then expressed as observable behaviour. This approach is referred to as ``computational neuroethology''. Computational neuroethology offers a firmer grounding for the semantics of the model, eliminating subjectivity from the result-interpretation process. A number of more fundamental implications of the approach are also discussed, chief of which is that insect cognition should be studied in preference to mammalian cognition. \end{abstract} An abridged version of this paper is to appear in: "From Animals to Animats: Proceedings of the First International Conference on the Simulation of Adaptive Behaviour" J.-A. Meyer and S.W. Wilson, editors. MIT Press/Bradford Books, 1990. --------------------------------------------------------------------------- Copies of the postscript file cliff.manifesto.Z may be obtained from the pub/neuroprose directory in cheops.cis.ohio-state.edu. Either use the Getps script or do this: unix-1> ftp cheops.cis.ohio-state.edu # (or ftp 128.146.8.62) Connected to cheops.cis.ohio-state.edu. Name (cheops.cis.ohio-state.edu:): anonymous 331 Guest login ok, sent ident as password. Password: neuron 230 Guest login ok, access restrictions apply. ftp> cd pub/neuroprose ftp> binary ftp> get cliff.manifesto.ps.Z ftp> quit unix-2> uncompress cliff.manifesto.ps.Z unix-3> lpr -P(your_local_postscript_printer) cliff.manifesto.ps ---------------------------------------------------------------------------- Or, order a hardcopy by sending your physical mail address to davec@cogs.sussex.ac.uk, mentioning CSRP162. Please do this only if you cannot use the ftp method described above. ------------------------------ End of Neuron Digest [Volume 6 Issue 64] ****************************************