Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!uflorida!mephisto!udel!princeton!pucc!PSYCH@TCSVM From: harnad@phoenix.Princeton.EDU (Stevan Harnad) Newsgroups: sci.psychology.digest Subject: PSYCOLOQUY V1 #10 (announcements : 408 lines) Message-ID: <9008081849.AA10848@suspicion.Princeton.EDU> Date: 8 Aug 90 15:20:04 GMT Sender: VMNNPOST@pucc.Princeton.EDU (Listserv to Netnews Gateway) Organization: Listserv to Netnews Gateway at pucc.Princeton.EDU Lines: 404 Approved: PSYCH@TCSVM PSYCOLOQUY Wed, 8 Aug 90 Volume 1 : Issue 10 PsychSearch Call for Papers - ICGA-91 IJPRAI CALL FOR PAPERS Short course announcement EJEP CALL FOR PAPERS GATB MEMO ---------------------------------------------------------------------- From: "[DCJPSY]KONOWEL" Subject: PsychSearch In June a land mail announcement was sent to some 1275 Psychology department chairs offering a demonstration of the new PsychNet online literature search facility PsychSearch. There is no cost nor any obligation associated with this demonstration offer. If your department would like to arrange for such a demonstration or requires additional information, please contact me at KONOWEL@DCJPSY.DAS.NET or by phone at 800-541-2598. The PsychSearch Library is the first online system able to provide full text article retrieval as well as an abstract searching facility. Thanks Lee Konowe ------------------------------ From: booker@AIC.NRL.Navy.Mil Subject: Call for Papers - ICGA-91 Call for Papers ICGA-91 The Fourth International Conference on Genetic Algorithms The Fourth International Conference on Genetic Algorithms (ICGA-91), will be held on July 13-16, 1991 at the University of California - San Diego in La Jolla, CA. This meeting brings together an international community from academia, government, and industry interested in algorithms suggested by the evolutionary process of natural selection. Topics of particular interest include: genetic algorithms and classifier systems, machine learning and optimization using these systems, and their relations to other learning paradigms (e.g., connectionist networks). Papers discussing how genetic algorithms and classifier systems are related to biological modeling issues (e.g., evolution of nervous systems, computational ethology, artificial life) are encouraged. Papers describing significant, unpublished research in this area are solicited. Authors must submit four (4) complete copies of their paper, postmarked by February 1, 1991, to the Program Co-Chair: Dr. Richard K. Belew Computer Science & Engr. Dept. (C-014) Univ. California - San Diego La Jolla, CA 92093 Electronic submissions (LaTeX source only) can be mailed to rik@cs.ucsd.edu. Papers should be no longer than 10 pages, single spaced, and printed using 12 pt. type. All papers will be subject to peer review. Evaluation criteria include the significance of results, originality, and the clarity and quality of the presentation. Important Dates: February 1, 1991: Submissions must be postmarked March 22, 1991: Notification to authors mailed May 6, 1991: Revised, final camera-ready paper due July 13-16, 1991: Conference dates ICGA-91 Conference Committee: Conference Co-Chairs: Kenneth A. De Jong, George Mason University J. David Schaffer, Philips Labs Vice Chair and Publicity: David E. Goldberg, Univ. of Illinois at Urbana-Champaign Program Co-Chairs: Richard K. Belew, U. of California at San Diego Lashon B. Booker, MITRE Financial Chair: Gil Syswerda, BBN Local Arrangements: Richard K. Belew, U. of California at San Diego ------------------------------ From: skrzypek%CS.UCLA.EDU@pucc (Dr. Josef Skrzypek) Subject: IJPRAI CALL FOR PAPERS 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. ------------------------------ From: BRUCE WHITEHEAD Subject: Short course announcement SHORT COURSE ANNOUNCEMENT Genetic Algorithms and Neural Networks October 17-19, 1990 University of Tennessee Space Institute Tullahoma, TN 37388 COURSE SUMMARY: Genetic algorithms and neural networks are artificial intelligence systems which do not require expert knowledge to be built into them. Specific knowledge about an application domain is neither programmed into these systems nor specified in rules. Instead, these systems learn from examples. Knowledge about a given application domain is automatically acquired by the system from example data points which are representative of the domain or task to be learned. These systems can therefore be used in applications where it would be difficult or impractical to completely specify the desired task in a set of rules, formulas, or programs. While learning from examples makes genetic algorithms and neural networks powerful, flexible, and easy to use, they are not magic. Successfully tailoring either of these systems to a complex, real- world problem requires a fundamental understanding of how these systems process information and how they learn. These systems cannot be treated as black boxes; there are choices of architectures to be considered and many parameters to be tuned before good results can be expected in a given application. The course objective is therefore to understand the underlying principles, capabilities, and limitations of these systems well enough to be able (i) to judge, for a given application, whether either a genetic algorithm or neural network approach would be advisable; and if so, (ii) to choose a specific architecture and a specific adaptation/learning procedure well-suited to that application; and finally, (iii) to knowledgeably apply the chosen genetic algorithm or neural network technique -- understanding its inner workings well enough to know whether it is doing what it should be, and if not, to experiment with different architectures and parameter settings intelligently rather than blindly. FOR FURTHER INFORMATION: For enrollment/fee information, travel and lodging information, etc., please contact the UTSI short course office: Short Course Office Sandra Shankle University of Tennessee Space Institute Tullahoma, TN 37388 615-455-0631, ext. 276 For technical questions about the course content, please contact the course director: Bruce Whitehead University of Tennessee Space Institute Tullahoma, TN 37388 615-455-0631, ext. 296 e-mail: whitehead_f@utsiv1.bitnet or whitehea@utkvx.bitnet or whitehea@utkvx.utk.edu INSTRUCTORS: David E. Goldberg is an Associate Professor of General Engineering at the University of Illinois at Urbana-Champaign. Prior to completing his Ph.D. at the University of Michigan, he held a number of positions in industry and the public sector. Following doctoral studies he held positions on the faculty of the University of Alabama, where he authored "Genetic Algorithms in Search, Optimization, and Machine Learning" (Addison-Wesley, 1989). He is currently investigating the foundations of genetic algorithms and messy genetic algorithms. Bruce A. Whitehead is an Associate Professor of Computer Science at the University of Tennessee Space Institute. His Ph.D. was received from the University of Michigan in 1977 for a neural network model of human pattern recognition. He is currently engaged in basic research in neural network architectures and applied research in rocket engine failure detection using neural networks. COURSE SCHEDULE (ALL TIMES ARE CENTRAL DAYLIGHT TIME) WEDNESDAY, OCTOBER 17, 8:30-12:00 Fundamental Principles of Neural Networks (Whitehead): Synopsis of useful concepts from linear (vector) algebra. Feedforward architectures based on neurons which implement decision surfaces; how neural networks learn from examples; supervised learning based on gradient descent error minimization; unsupervised learning based on competitive similarity measures; basic neural network architectures based on these principles. WEDNESDAY, OCTOBER 17, 1:00-4:30 Lab in Neural Networks (Whitehead): Explanation of and experimentation with software modules which implement each of the fundamental principles discussed in the morning session. [Note: Students with a potential application in mind are encouraged to bring sample data for this application, to experiment with as desired and to get a feel for what a neural network would do with it. If you wish to bring such a data set, please check with Bruce Whitehead (e-mail & phone listed above) to make sure your data is in a format compatible with the software we will be using in the lab.] THURSDAY, OCTOBER 18, 8:30-12:00 Fundamental Principles of Genetic Algorithms (Goldberg): How genetic algorithms differ from conventional optimization methods; similarity templates considered as schemata and as hyperplanes; intrinsic parallelism; the building block hypothesis; the fundamental genetic operators of reproduction, crossover, and mutation. THURSDAY, OCTOBER 18, 1:00-4:30 Lab in Genetic Algorithms (Goldberg): Explanation of software modules based on the fundamental principles discussed in the morning session; the structure of a simple genetic algorithm composed of these modules; experimentation with the simple genetic algorithm. FRIDAY, OCTOBER 19, 8:30-12:00 Genetic Algorithm Architectures and Methods (Goldberg): Objective functions and fitness scaling; strategies for encoding the problem domain; encoding constraints; advanced operators and techniques in genetic search; niche and separation methods; applications of genetic algorithms; introduction to genetics-based machine learning. FRIDAY, OCTOBER 19, 1:00-4:30* Neural Network Architectures and Methods (Whitehead): Taxonomy and comparison of the major types of neural network architectures and learning methods, including the strengths and weaknesses of each. In-depth examination of a few representative architectures, including those based on supervised learning (such as back propagation, counter propagation, and the learning vector quantizer) and those based on unsupervised learning (such as the topology- preserving feature map). What types of applications are suitable for neural network implementations. Comparison of neural networks and genetic algorithms with each other and with conventional computer science and mathematical methods. *Note: Dr. Whitehead and the lab facilities will continue to be available Friday evening and/or Saturday morning for any course participants who wish to individually discuss or experiment with their potential applications. ------------------------------ From: "[DCJPSY]KONOWEL" Subject: EJEP CALL FOR PAPERS The Electronic Journal of Experimental Psychology is seeking articles for on-line publication. This refereed journal is edited by Lloyd Shewchuk and is published by PsychNet, Inc. The Journal has an ISSN number and is archieved by the Library of Congress. Articles may be of any length. Submissions should be made to: PsychNet, Inc. EJEP 80 Topstone Road Ridgefield, CT 06877 ------------------------------ From: "C. Fullerton" Subject: GATB MEMO M E M O R A N D U M To: All interested parties From: Dianne C. Brown Subject: Proposed Policy Guidance on the General Aptitude Test Battery The General Aptitute Test Battery (GATB), used by state employment agencies for selection and career counseling, has become the center of controversy over the use of within-group scoring methods. In response to criticisms of the within-group scoring methods, designed to reduce adverse impact against protected groups, the Department of Labor (DOL) will be discontinuing the use of the GATB for employment selection purposes for a two year period during which extensive research of the test will be conducted. During this period the GATB may still be used as a career counseling device on a voluntary basis, or at the request of the individual.The research plan addresses recommendations made by the National Academy of Science (NAS) following their intensive study of the GATB. The Employment and Training Administration of DOL has released its proposed policy guidance on the GATB for public review and comment. Released in the July 24 Federal Register, Vol. 55, No. 142, page 30162, comments to the statement are requested by August 23, 1990. The final statement and subsequent discontinuation of the GATB are scheduled for 90 days following the release of the proposed statement (or October 23). The American Psychological Association will be submitting comments on the proposed guideline and urges its membership with expertise in this area to also submit comments on behalf of their institutions or as individuals. Please send a copy of any comments you may develop to: Dianne C. Brown American Psychological Association 1200 Seventeenth Street, N.W. Washington, D.C. 20036 ------------------------------ PSYCOLOQUY is sponsored by the Science Directorate of the American Psychological Association (202) 955-7653 Co-Editors: (scientific discussion) (professional/clinical discussion) Stevan Harnad Perry London Psychology Department Dean, Graduate School of Princeton University Applied and Professional Psychology Rutgers University Assistant Editors: Malcolm Bauer John Pizutelli Psychology Department Psychology Department Princeton University Rutgers University End of PSYCOLOQUY Digest ******************************