neuron-request@HPLMS2.HPL.HP.COM ("Neuron-Digest Moderator Peter Marvit") (09/19/90)
Neuron Digest Tuesday, 18 Sep 1990 Volume 6 : Issue 54 Today's Topics: why models that have similar illusions are useful (re: S. Lehar) Anyone using Eldelman's theories? INNS/SIG Washington Technical Meeting request for data Natural Language Parsing Request for replies ML91 -- THE EIGHTH INTERNATIONAL WORKSHOP ON MACHINE LEARNING NN For Knowledge Representation and Inference TR - Acquiring Verb Morphology in Children and Connectionist Nets Reinforcement Learning -- Special Issue of Machine Learning Journal ANNA-91 Conference Tech Report Available - ID3 vs. BackProp NN AND VISION -IJPRAI-special issue 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: why models that have similar illusions are useful (re: S. Lehar) From: "David A. Honig" <honig@ICS.UCI.EDU> Date: Mon, 10 Sep 90 15:21:18 -0700 Steve Lehar Boston University Boston MA WROTE: "The BCS/FCS is a very interesting model mostly because it does not just try to perform image processing with neural techniques, but actually attempts to duplicate the exact neural architecture used by the brain. The model is based not only on neurophysiological findings, but much of the model is directly based on visual illusions- things that the human eye sees that arn't really there! The idea is that if we can model the illusions as well as the vision, then we will have a mechanism that not only does the same job as the eye, but does it the same way as the eye does. Imagine if you were given a primitive pocket calculator, and asked to figure out how it works without taking it apart. Giving it calculations like 1+1= will not make you any the wiser. When you ask it to compute (1/3)*3= however you will learn not only how it works, but also how it fails. The BCS/FCS is the only model that can explain a wide range of psychophysical phenomena such as neon color spreading, pre-attentive perceptual grouping, mach bands, brightness and color illusions, illusory boundaries and illusory motions of various sorts." Connectionists interested in this reasoning, and in the important relationship between functionality, algorithm, and implementation, and how these should be analyzed, might want to read David Marr's book, _Vision_ (WH Freeman & Co, 1982). ------------------------------ Subject: Anyone using Eldelman's theories? From: anumolu@cis.uab.edu (Vivek Anumolu) Date: Mon, 10 Sep 90 21:15:29 -0500 hello fellow NN researchers, There has been some recent excitement about Gerald Edelman's theory of Neuronal Group Selection. If the theory has a lot of promise, why don't many researchers work on this theory? Specifically I 'm interested in any references to any type of analysis or application of this theory by folks other than the Edelman group. Thanks. Vivek Anumolu anumolu@cis.uab.edu /* INTERNET address */ ------------------------------ Subject: INNS/SIG Washington Technical Meeting From: Gary Fleming <72260.2544@compuserve.com> Date: 11 Sep 90 09:30:49 -0400 INTERNATIONAL NEURAL NETWORK SOCIETY GREATER WASHINGTON AREA SPECIAL INTEREST GROUP The INNS/SIG Washington is pleased to announce a technical meeting to be held at 7:00 pm, 19 September 1990 in the Lipsett Amphitheater in the Clinical Center, National Institutes of Health. Dr. Charles Wilson of the National Institute of Standards and Technology (NIST, formerly the National Bureau of Standards) will speak on Self-Organizing Neural Network Character Recognition on Massively Parallel Computers The NIH campus is accessible by MetroRail or by automobile. If you arrive by Metro, the Clinical Center is the large 10 story building to the East-NorthEast of the Metro Station. If you arrive by automobile, the NIH campus is approximately 1 mile south of the Capital Beltway on Wisconsin Avenue (or Rockville Pike). Upon entering the Clinical Center, bear left and progress towards the Lipsett Amphitheater. For further information, please call Gary Fleming at (301) 459-4343. ABSTRACT Neural network based methods for image filtering and pattern feature extraction are combined to develop font independent character recognition on a massively parallel array processor. Feature localization and noise reduction are achieved using least squares optimized Gabor filtering. The filtered images are then presented to an ART-1 based learning algorithm which produces the self-organizing sets of neural network generated features used for character recognition. Implementation of these algorithms on highly parallel computer with 1024 processors allows high speed character recognition to be achieved at a speed of 3ms/image, with greater than 99.9\% accuracy on machine print and 80\% accuracy on unconstrained hand printed characters. To improve the accuracy of hand printed recognition a new architecture was developed for for multi-map, self-organizing pattern recognition which allows concurrent, massively parallel, learning of features using different maps for each feature type. The method used is similar to the multi-map maps known to exist in the vertebrate sensory cortex. The method consists sets of associative memory locations, one for each feature type, in which learning is symmetrically triggered by logical combinations of the association strengths of the memory blocks. Each map is independent of the others except for the connections used to trigger learning. The learning used to update memory location uses a feed forward mechanisms and is self-organizing. The architecture is described by the acronym FAUST (Feed-forward Association Using Symmetrical Triggering). As a demonstration of the effectiveness of FAUST, 99.9\% accurate character recognition on medium quality machine printed digits at 2 ms/digit and 90\% recognition with 2\% substitutional errors has been achieved on hand printed digits. REFERENCES [1] G. A. Carpenter, S. Grossberg and C. Mehanian, ``Invariant Recognition of Cluttered Scenes by a Self-Organizing ART Architecture: CORT-X Boundary Segmentation'', Neural Networks, 2, pp. 169-181, 1989. [2] B. L. Pulito, T. R. Damarla, and S. Nariani, ``A Two- Dimensional Shift Invarient Image Classification Neural Network Which Overcomes the Stability/Plasticty Delemma'', Proc. of the IJCNN, II, pp. 825-833, June 1990. [3] C. L. Wilson, R. A. Wilkinson, and M. D. Garris, ``Self- Organizing Neural Network Character Recognition on a Massively Parallel Computer'', Proc. of the IJCNN, II, pp. 325-329, June 1990. [4] G. A. Carpenter and S. Grossberg, ``A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine'', Computer Vision, Graphics, and Image Processing, 37, pp 54-115, 1987. [5] K. Fukushima, ``Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shifts in position'', Biological Cybernetics, 36, pp. 193-202, 1980. [6] J. G. Daugman, `` Complete Discrete 2-D Gabor Transform by Neural Networks for Image Analysis and Compression'', IEEE Trans on Acoustics, Speech, and Signal Processing, 36,pp. 1169-1179, 1988. [7] R. Linsker, ``Self-Organization in a Perceptual Network'', Computer, 21, pp. 105-117, 1988. [8] J. Rubner and K. Schulten, ``Development of Feature Detectors by Self-Organization'', Biological Cybernetics, 62, pp. 193-199, 1990. [9] A. Rojer and E. Schwatz, ``Multi-Map Model for Pattern Classification'', Neural Computation, 1, pp. 104-115, 1989. [10] D. L. Alkon, K. T. Blackwell, G. S. Barbour, A. K. Rigler, and T. P. Vogl, ``Pattern-Recognition by an Artificial Network Derived fron Biological Neuronal Systems'', Biological Cybernetics, 62, pp. 363-376, 1990. [11] P. M. Flanders, D. J. Hunt, S. F. Reddaway, and D. Parkinson, ``Efficient high speed computing with the distributed array processor'', Proceedings of Symposium on High Speed Computer and Algorithm Organization, U of Ill., pp. 113-128, 1977. ------------------------------ Subject: request for data From: zamora@das.llnl.gov (John A. Zamora) Date: Tue, 11 Sep 90 10:50:58 -0700 I am a graduate student conducting research in the area of neural networks. Since this is a neural network newsgroup, I would like to ask those of you in netland for some possible help. This research is looking at the possibility of a correlation between neural networks and other organized systems. So the research is in need of data for statistical purposes. At this point, backpropagation is the type of neural network being considered. Specifically, the data requested would be as follows: * The title of the problem being solved and your name. * The number of nodes in the input, hidden, and output layer. * Did you use the standard backpropagation formula? Did you use a momentum term in your formula? * The weight values between nodes of a neural network after training. Your time is greatly appreciated in this matter. If you have more than one set of weights available (two or three sets), this will be of great help. If you have any questions, please do not hesitate to contact me. John Zamora (415) 422-2008 zamora@das.llnl.gov Thank you for your time and effort. John A. Zamora zamora@das.llnl.gov (415) 422-2008 "All necessary disclaimers apply" ------------------------------ Subject: Natural Language Parsing From: E S Atwell <eric%ai.leeds.ac.uk@pucc.PRINCETON.EDU> Date: Wed, 12 Sep 90 14:39:28 +0000 I'm looking for references on neural networks for Natural Language parsing, including techniques for parsing language of at least Context Free complexity, and/or using a recursive stack of NNs. I have a large collection of parsed English sentences (words plus detailed syntax trees) that I'd love to train a neural network stack with if only I knew how. Any leads will be appreciated. I will summarise and return the list to any responses. Thanks. Eric Steven Atwell Centre for Computer Analysis of Language And Speech (CCALAS) Artificial Intelligence Division, School of Computer Studies phone: +44 532 335761 Leeds University FAX: +44 532 335468 Leeds LS2 9JT JANET: eric@uk.ac.leeds.ai England EARN/BITNET/ARPA: eric%leeds.ai@ac.uk ------------------------------ Subject: Request for replies From: Ralph Cherubini <cherubini@austin.enet.dec.com> Date: Thu, 13 Sep 90 06:49:44 -0700 I am interested in any information on ways to characterize the effects of additive noise in back-propagation connection weights on network performance. More specifically: has anyone done any work on a characterization which expresses the effects in terms of analogy with optical focussing? I am not particularly interested in ways of quantifying robustness of performance in the presence of noise. Thank you in advance for any thoughts, Ralph Cherubini Digital Equipment Corporation ------------------------------ Subject: ML91 -- THE EIGHTH INTERNATIONAL WORKSHOP ON MACHINE LEARNING From: Lawrence Birnbaum <birnbaum@fido.ils.nwu.edu> Date: Fri, 07 Sep 90 10:03:56 -0500 ML91 -- THE EIGHTH INTERNATIONAL WORKSHOP ON MACHINE LEARNING CALL FOR WORKSHOP PROPOSALS AND PRELIMINARY CALL FOR PAPERS On behalf of the organizing committee, we are pleased to solicit proposals for the workshops that will constitute ML91, the Eighth International Workshop on Machine Learning, to be held in late June, 1991, at Northwestern University, Evanston, Illinois, USA. We anticipate choosing six workshops to be held in parallel over the three days of the meeting. Our goal in evaluating workshop proposals is to ensure high quality and broad coverage of work in machine learning. Workshop committees -- which will operate for the most part independently in selecting work to be presented at ML91 -- should include two to four people, preferably at different institutions. The organizing committee may select some workshops as proposed, or may suggest changes or combinations of proposals in order to achieve the goals of quality and balance. Proposals are due October 10, 1990, preferably by email to: ml91@ils.nwu.edu although hardcopy may also be sent to the following address: ML91 Northwestern University The Institute for the Learning Sciences 1890 Maple Avenue Evanston, IL 60201 USA fax (708) 491-5258 Please include the following information: 1. Workshop topic 2. Names, addresses, and positions of workshop committee members 3. Brief description of topic 4. Workshop format 5. Justification for workshop, including assessment of breadth of appeal Workshop format is somewhat flexible, and may include invited talks, panel discussions, short presentations, and even small working group meetings. However, it is expected that the majority of time will be devoted to technical presentations of 20 to 30 minutes in length, and we encourage the inclusion of a poster session in each workshop. Each workshop will be allocated approximately 100 pages in the Proceedings, and papers to be published must have a minimum length of (most likely) 4 to 5 pages in double column format. Workshop committee members should be aware of these space limitations in designing their workshops. We encourage proposals in all areas of machine learning, including induction, explanation-based learning, connectionist and neural net models, adaptive control, pattern recognition, computational models of human learning, perceptual learning, genetic algorithms, computational approaches to teaching informed by learning theories, scientific theory formation, etc. Proposals centered around research problems that can fruitfully be addressed from a variety of perspectives are particularly welcome. The workshops to be held at ML91 will be announced towards the end of October. In the meantime, we would like to announce a preliminary call for papers; the submission deadline is February 1, 1990. Authors should bear in mind the space limitations described above. On behalf of the organizing committee, Larry Birnbaum Gregg Collins Program co-chairs, ML91 (This announcement is being sent/posted to ML-LIST, CONNECTIONISTS, ALife, PSYCOLOQUY, NEWS.ANNOUNCE.CONFERENCES, COMP.AI, COMP.AI.EDU, COMP.AI.NEURAL-NETS, COMP.ROBOTICS, and SCI.PSYCHOLOGY. We encourage readers to forward it to any other relevant mailing list or bulletin board.) ------------------------------ Subject: NN For Knowledge Representation and Inference From: B344DSL@UTARLG.UTARL.EDU Date: Sat, 08 Sep 90 18:41:00 -0500 Announcement NEURAL NETWORKS FOR KNOWLEDGE REPRESENTATION AND INFERENCE Fourth Annual Workshop of the Metroplex Institute for Neural Dynamics (MIND) October 4-6, 1990 IBM Westlake, TX (near Dallas - Fort Worth Airport) Conference Organizers: Daniel Levine, University of Texas at Arlington (Mathematics) Manuel Aparicio, IBM Application Solutions Division Speakers will include: James Anderson, Brown University (Psychology) Jean-Paul Banquet, Hospital de la Salpetriere, Paris John Barnden, New Mexico State University (Computer Science) Claude Cruz, Plexus Systems Incorporated Robert Dawes, Martingale Research Corporation Richard Golden, University of Texas at Dallas (Human Development) Janet Metcalfe, Dartmouth College (Psychology) Jordan Pollack, Ohio State University (Computer Science) Karl Pribram, Radford University (Brain Research Institute) Lokendra Shastri, University of Pennsylvania (Computer Science) Topics will include: Connectionist models of semantic comprehension. Architectures for evidential and case-based reasoning. Connectionist approaches to symbolic problems in AI such as truth maintenance and dynamic binding. Representations of logical primitives, data structures, and constitutive relations. Biological mechanisms for knowledge representation and knowledge-based planning. We plan to follow the talks by a structured panel discussion on the questions: Can neural networks do numbers? Will architectures for pattern matching also be useful for precise reasoning, planning, and inference? Tutorial Session: Robert Dawes, President of Martingale Research Corporation, will present a three hour tutorial on neurocomputing the evening of October 3. This preparation for the workshop will be free of charge to all pre-registrants. ------------------------------------------------------------------------ Registration Form NEURAL NETWORKS FOR KNOWLEDGE REPRESENTATION AND INFERENCE Fourth Annual Workshop of the Metroplex Institute for Neural Dynamics (MIND) Name: _____________________________________________________ Affiliation: ______________________________________________ Address: __________________________________________________ __________________________________________________ __________________________________________________ __________________________________________________ Telephone number: _________________________________________ Electronic mail: __________________________________________ Conference fee enclosed (please check appropriate line): $50 for MIND members before September 30 ______ $60 for MIND members on/after September 30 ______ $60 for non-members before September 30 ______ $70 for non-members on/after September 30 ______ $10 for student MIND members any time ______ $20 for student non-members any time ______ Tutorial session (check if you plan to attend): ______ Note: This is free of charge to pre-registrants. Suggested Hotels: Solana Marriott Hotel. Next to IBM complex, with continuous shuttle bus available to meeting site; ask for MIND conference rate of $80/night. Call (817) 430-3848 or (800) 228-9290. Campus Inn, Arlington. 30 minutes from conference, but rides are available if needed; $39.55 for single/night. Call (817) 860-2323. American Airlines. Minus 40% on coach or 5% over and above Super Saver. Call (800)-433-1790 for specific information and reservations, under Star File #02oz76 for MIND Conference. Conference programs, maps, and other information will be mailed to pre-registrants in mid-September. Please send this form with check or money order to: Dr. Manuel Aparicio IBM Mail Stop 03-04-40 5 West Kirkwood Blvd. Roanoke, TX 76299-0001 (817) 962-5944 ------------------------------ Subject: TR - Acquiring Verb Morphology in Children and Connectionist Nets From: Kim Plunkett <plunkett@amos.ucsd.edu> Date: Mon, 10 Sep 90 11:37:33 -0700 The following TR is now available: From Rote Learning to System Building: Acquiring Verb Morphology in Children and Connectionist Nets Kim Plunkett University of Aarhus Denmark Virginia Marchman Center for Research in Language University of California, San Diego Abstract The traditional account of the acquisition of English verb morphology supposes that a dual mechanism architecture underlies the transition from early rote learning processes (in which past tense forms of verbs are correctly produced) to the systematic treatment of verbs (in which irregular verbs are prone to error). A connectionist account supposes that this transition can occur in a single mechanism (in the form of a neural network) driven by gradual quantitative changes in the size of the training set to which the network is exposed. In this paper, a series of simulations is reported in which a multi-layered perceptron learns to map verb stems to past tense forms analogous to the mappings found in the English past tense system. By expanding the training set in a gradual, incremental fashion and evaluat- ing network performance on both trained and novel verbs at successive points in learning, we demonstrate that the net- work undergoes reorganizations that result in a shift from a mode of rote learning to a systematic treatment of verbs. Furthermore, we show that this reorganizational transition is contingent upon a critical mass in the training set and is sensitive to the phonological sub-regularities character- izing the irregular verbs. The optimal levels of performance achieved in this series of simulations compared to previous work derives from the incremental training procedures exploited in the current simulations. The pattern of errors observed are compared to those of children acquiring the English past tense, as well as children's performance on experimental studies with nonsense verbs. Incremental learn- ing procedures are discussed in light of theories of cogni- tive development. It is concluded that a connectionist approach offers a viable alternative account of the acquisi- tion of English verb morphology, given the current state of empirical evidence relating to processes of acquisition in young children. Copies of the TR can be obtained by contacting "staight@amos.ucsd.edu" and requesting CRL TR #9020. Please remember to provide your hardmail address. Alternatively, a compressed PostScript file is available by anonymous ftp from "amos.ucsd.edu" (internet address 128.54.16.43). The relevant file is "crl_tr9020.ps.Z" and is in the directory "~ftp/pub". Kim Plunkett ------------------------------ Subject: Reinforcement Learning -- Special Issue of Machine Learning Journal From: Rich Sutton <rich@gte.com> Date: Wed, 12 Sep 90 11:36:48 -0400 CALL FOR PAPERS The journal Machine Learning will be publishing a special issue on REINFORCEMENT LEARNING in 1991. By "reinforcement learning" I mean trial-and-error learning from performance feedback without an explicit teacher other than the external environment. Of particular interest is the learning of mappings from situation to action in this way. Reinforcement learning has most often been studied within connectionist or classifier-system (genetic) paradigms, but it need not be. Manuscripts must be received by March 1, 1991, to assure full consideration. One copy should be mailed to the editor: Richard S. Sutton GTE Laboratories, MS-44 40 Sylvan Road Waltham, MA 02254 USA In addition, four copies should be mailed to: Karen Cullen MACH Editorial Office Kluwer Academic Publishers 101 Philip Drive Assinippi Park Norwell, MA 02061 USA Papers will be subject to the standard review process. ------------------------------ Subject: ANNA-91 Conference From: /PN=HARRY.ERWIN/O=TRW/ADMD=TELEMAIL/C=US/@sprint.com Date: 13 Sep 90 17:41:00 +0000 ANNA-91: Analysis of Neural Net Applications Conference May 29-31, 1991, George Mason University, Fairfax, VA CALL FOR PARTICIPATION The 1991 Analysis of Neural Net Applications Conference, ANNA-91, will present a single-track technical program focusing on the applications of neural net technology to real world problems. The program will be structured around the problem-solving process: . Domain Analysis . Design Criteria . Analytic Approaches to Network Definition . Evaluation Mechanisms . Lesson Learned, Feedback/Design Implications Authors are invited to report about concrete results and experiences on the application of neural nets. Reports about important negative, as well as successful, results are encouraged. Submissions should address applications areas, such as: . Biological applications . Cognitive modeling . Modeling of linear and non-linear systems . Optimization and decision support . Vision and imaging Authors are responsible for any necessary clearances and/or approvals for submitted abstracts and papers. ACM copyright releases will be required for the final papers. Authors are expected to provide their full papers to be included in the proceedings, which will be available at the conference. Please submit 10 copies of an extended abstract of sufficient length to support review--4-5 pages, including a brief bibliography. Authors of accepted papers are expected to provide full papers for the proceedings, not to exceed 25 pages, including bibliography. Tutorial sessions will be held on Wednesday, May 29, immediately prior to the conference. If you are interested in teaching a tutorial or feel a need for one in a particular related field, please submit a full-day tutorial proposal. Instructors should include one copy of draft tutorial notes and descriptions of any demonstrations with 10 copies of their proposal. Instructors of accepted tutorials are expected to provide a master set of tutorial notes, not to exceed 200 pages including bibliography, for distribution to tutorial attendees. Key Dates: . Submission deadline: 11/15/90. . Acceptance notices: 1/1/91. . Final paper due: 2/28/91. . Tutorial date: 5/29/91. . Conference dates: 5/30-31/91. All submissions should be sent to: Robert Stites ANNA-91 Program Chair IKONIX PO Box 565 Herndon, VA 22070-0565 For ANNA-91 information, contact: Toni Shetler ANNA-91 Conference Chair TRW/Systems Division FVA6/3444 PO Box 10400 Fairfax, VA 22031 Sponsors: ACM SIGArt, ACM SIGBDP In cooperation with: International Neural Net Society Washington Evolutionary Systems Society Institutional support: George Mason University National Institutes of Health Industrial support: American Electronics Inc. CTA Inc. TRW/Systems Division Harry Erwin Telemail: HERWIN/TRW Internet: /G=Harry/S=Erwin/O=TRW/ADMD=Telemail/C=US/@Sprint.com Alternate Internet: herwin@pro-novapple.cts.com ------------------------------ Subject: Tech Report Available - ID3 vs. BackProp From: Tom Dietterich <tgd@turing.CS.ORST.EDU> Date: Thu, 13 Sep 90 14:08:26 -0700 The following tech report is available in compressed postscript format from the neuroprose archive at Ohio State. A Comparison of ID3 and Backpropagation for English Text-to-Speech Mapping Thomas G. Dietterich Hermann Hild Ghulum Bakiri Department of Computer Science Oregon State University Corvallis, OR 97331-3102 Abstract The performance of the error backpropagation (BP) and decision tree (ID3) learning algorithms was compared on the task of mapping English text to phonemes and stresses. Under the distributed output code developed by Sejnowski and Rosenberg, it is shown that BP consistently out-performs ID3 on this task by several percentage points. Three hypotheses explaining this difference were explored: (a) ID3 is overfitting the training data, (b) BP is able to share hidden units across several output units and hence can learn the output units better, and (c) BP captures statistical information that ID3 does not. We conclude that only hypothesis (c) is correct. By augmenting ID3 with a simple statistical learning procedure, the performance of BP can be approached but not matched. More complex statistical procedures can improve the performance of both BP and ID3 substantially. A study of the residual errors suggests that there is still substantial room for improvement in learning methods for text-to-speech mapping. This is an expanded version of a short paper that appeared at the Seventh International Conference on Machine Learning at Austin TX in June. To retrieve via FTP, use the following procedure: unix> ftp cheops.cis.ohio-state.edu # (or ftp 128.146.8.62) Name (cheops.cis.ohio-state.edu:): anonymous Password (cheops.cis.ohio-state.edu:anonymous): <ret> ftp> cd pub/neuroprose ftp> binary ftp> get (remote-file) dietterich.comparison.ps.Z (local-file) foo.ps.Z ftp> quit unix> uncompress foo.ps unix> lpr -P(your_local_postscript_printer) foo.ps ------------------------------ Subject: NN AND VISION -IJPRAI-special issue From: "Dr. Josef Skrzypek" <skrzypek@CS.UCLA.EDU> Date: Thu, 13 Sep 90 15:25:48 -0700 Because of repeat enquiries about the special issue of IJPRAI (Intl. J. of Pattern Recognition and AI) I am posting the announcement again. IJPRAI CALL FOR PAPERS IJPRAI We are organizing a special issue of IJPRAI (Intl. Journal of Pattern Recognition and Artificial Intelligence) dedicated to the subject of neural networks in vision and pattern recognition. Papers will be refereed. The plan calls for the issue to be published in the fall of 1991. I would like to invite your participation. DEADLINE FOR SUBMISSION: 10th of December, 1990 VOLUME TITLE: Neural Networks in Vision and Pattern Recognition VOLUME GUEST EDITORS: Prof. Josef Skrzypek and Prof. Walter Karplus Department of Computer Science, 3532 BH UCLA Los Angeles CA 90024-1596 Email: skrzypek@cs.ucla.edu or karplus@cs.ucla.edu Tel: (213) 825 2381 Fax: (213) UCLA CSD DESCRIPTION The capabilities of neural architectures (supervised and unsupervised learning, feature detection and analysis through approximate pattern matching, categorization and self-organization, adaptation, soft constraints, and signal based processing) suggest new approaches to solving problems in vision, image processing and pattern recognition as applied to visual stimuli. The purpose of this special issue is to encourage further work and discussion in this area. The volume will include both invited and submitted peer-reviewed articles. We are seeking submissions from researchers in relevant fields, including, natural and artificial vision, scientific computing, artificial intelligence, psychology, image processing and pattern recognition. "We encourage submission of: 1) detailed presentations of models or supporting mechanisms, 2) formal theoretical analyses, 3) empirical and methodological studies. 4) critical reviews of neural networks applicability to various subfields of vision, image processing and pattern recognition. Submitted papers may be enthusiastic or critical on the applicability of neural networks to processing of visual information. The IJPRAI journal would like to encourage submissions from both , researchers engaged in analysis of biological systems such as modeling psychological/neurophysiological data using neural networks as well as from members of the engineering community who are synthesizing neural network models. The number of papers that can be included in this special issue will be limited. Therefore, some qualified papers may be encouraged for submission to the regular issues of IJPRAI. SUBMISSION PROCEDURE Submissions should be sent to Josef Skrzypek, by 12-10-1990. The suggested length is 20-22 double-spaced pages including figures, references, abstract and so on. Format details, etc. will be supplied on request. Authors are strongly encouraged to discuss ideas for possible submissions with the editors. The Journal is published by the World Scientific and was established in 1986. Thank you for your considerations. ------------------------------ End of Neuron Digest [Volume 6 Issue 54] ****************************************