From dyyeung@cs.ust.hk Mon Sep 11 01:37:40 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 11 Sep 95 01:37:38 -0500; AA29478 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Mon, 11 Sep 95 01:37:36 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa14181; 11 Sep 95 1:02:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa14179; 11 Sep 95 0:42:57 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa26955; 11 Sep 95 0:42:27 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa02070; 11 Sep 95 0:19:29 EDT Received: from cssu46.cs.ust.hk by RI.CMU.EDU id aa10170; 11 Sep 95 0:17:30 EDT Received: from cssu35.cs.ust.hk (dyyeung@cssu35.cs.ust.hk [143.89.40.35]) by cssu46.cs.ust.hk (8.6.12/8.6.9) with ESMTP id MAA20191; Mon, 11 Sep 1995 12:12:30 +0800 Received: (from dyyeung@localhost) by cssu35.cs.ust.hk (8.6.12/8.6.9) id MAA16731; Mon, 11 Sep 1995 12:12:27 +0800 From: Dit-Yan Yeung Message-Id: <199509110412.MAA16731@cssu35.cs.ust.hk> Subject: Survey Paper on Constructive Neural Networks To: connectionists@cs.cmu.edu Date: Mon, 11 Sep 1995 12:12:27 +0800 (HKT) Cc: Dit-Yan Yeung X-Mailer: ELM [version 2.4 PL24] Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Content-Length: 1355 Paper (81596 bytes in gziped PS): ftp://ftp.cs.ust.hk/pub/techreport/95/tr95-43.ps.gz ******************************************************************************* Constructive Feedforward Neural Networks for Regression Problems: A Survey Tin-Yau Kwok & Dit-Yan Yeung Department of Computer Science Hong Kong University of Science and Technology Clear Water Bay, Kowloon Hong Kong {jamesk,dyyeung}@cs.ust.hk Technical Report HKUST-CS95-43 September 1995 ABSTRACT In this paper, we review the procedures for constructing feedforward neural networks in regression problems. While standard back-propagation performs gradient descent only in the weight space of a network with fixed topology, constructive procedures start with a small network and then grow additional hidden units and weights until a satisfactory solution is found. The constructive procedures are categorized according to the resultant network architecture and the learning algorithm for the network weights. ******************************************************************************* From rob@comec4.mh.ua.edu Mon Sep 11 12:53:05 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 11 Sep 95 12:53:01 -0500; AA04819 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Mon, 11 Sep 95 12:52:55 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA02326; Mon, 11 Sep 1995 18:36:01 +0800 Message-Id: <199509111036.SAA02326@cs.uwa.oz.au> From: Robert Elliott Smith To: reinforce@cs.uwa.edu.au Subject: Special AI session of SECTAM XVIII [connectionists] Date: Fri, 08 Sep 95 14:25:58 -0600 AI Techniques in Engineering and Mechanics A Special Session of EIGHTEENTH SOUTHEASTERN CONFERENCE ON THEORETICAL AND APPLIED MECHANICS April 14 - 16, 1996 TUSCALOOSA, ALABAMA Artificial Intelligence (AI) techniques are now being used by the practicing engineer to solve a whole range of heretofore intractable problems. This session will consist of paper presentations describing the practical application of AI in all branches of engineering and mechanics, and thus will serve as a forum for the transfer of knowledge in this rapidly developing field. Papers are welcome from individuals and research groups on the subject of applications of AI including, but not limited to, the following topics: Systems and techniques such as: Expert systems, knowledge acquisition, knowledge-based systems, interactive knowledge-based systems, intelligent CAD/CAM systems, signal processing, sensor and data fusion, adaptive learning systems, neural networks, performance analysis, machine-vision systems, deductive databases, knowledge representation, modelling, learning heuristics, intelligent control systems, fuzzy logic, and genetic algorithms. Engineering applications including: Manufacturing, industrial engineering, production engineering, chemical engineering, civil engineering, electrical engineering, mechanical engineering, process control, robotics, autonomous vehicles, and communication. To submit a paper to the special session, follow instructions in the general SECTAM XVIII announcement (included below). Please indicate that the paper is for the AI special session. Contact persons for information on the special session are: Robert E. Smith Phone: (205) 348-1618 Email: rob@comec4.mh.ua.edu and Charles L. Karr Phone: (205) 348-0066 Email: ckarr@buster.eng.ua.edu Department of Engineering Science and Mechanics University of Alabama Box 870278 Tuscaloosa, AL 35487 Fax: (205) 348-7240 ----------------------------------------------------------------- CALL FOR PAPERS SECTAM XVIII EIGHTEENTH SOUTHEASTERN CONFERENCE ON THEORETICAL AND APPLIED MECHANICS April 14 - 16, 1996 TUSCALOOSA, ALABAMA Hosted by The University of Alabama ABOUT THE CONFERENCE The Southeastern Conference on Theoretical and Applied Mechanics (SECTAM) has been held biannually since 1962 to provide a forum for researchers from all over the world to publish the results of their investigations and to promote the exchange of new ideas in theoretical and applied mechanics. During the past thirty-three years, SECTAM has gained an international reputation for high quality presentations and proceedings. Practitioners from industry, government, and education are invited to participate. The program consists of a keynote address and invited and contributed papers. TOPICS Original papers are solicited in all areas of theoretical and applied mechanics and related topics. Papers are especially sought in the areas of biomechanics and penetration/impact dynamics in which symposia are planned. If researchers would like to propose additional symposia in other areas, please contact H. B. Wilson. INSTRUCTIONS FOR AUTHORS Research results can be submitted either as an abstract or a full-length paper. Only full-length papers will be published in the hardback proceedings of the conference. Both abstracts and full-length papers will be reviewed. Accepted abstracts and full- length papers will be presented at the conference. Abstracts Abstracts are required for review by the Editorial Committee. Authors of accepted abstracts will present their work at the conference. Abstracts are limited to two single-spaced pages in length. Abstracts will be reprinted in a soft-cover collection and available for attendees at the conference. Full-length Papers Full-length papers are required for review by the Editorial Committee. Authors of accepted papers will be instructed to provide a complete camera-ready manuscript. Accepted papers will be presented at the conference and will be published in the hard-bound proceedings, which will be available at the time of the conference. Student Paper Competition After the successful student program introduced in 1992, SECTAM is proud to organize the Third Student Paper Competition. Student papers must be authored by students only. Faculty collaboration, if any, should be recognized in an acknowledgment section. Papers in this category will also be reviewed by the Editorial Committee and must adhere to the conference guidelines and deadlines. Authors of accepted papers will be instructed to provide a complete camera-ready manuscript for publication in the hard-bound proceedings and are expected to present their work at the conference. A panel of judges will evaluate paper presentations and select the best papers. Plaques and cash prizes will be awarded to the authors of the best papers during the conference. Awards for the best three papers are $300, $200, and $100. Specially Organized Technical Sessions and Panel Discussions Individuals and/or groups who wish to organize technical sessions or panel discussions focusing on specific technical issues of current interest should write to the Conference Executive Chair by June 30, 1995 describing the proposed session. Full- length papers for these special sessions must be submitted to the Editorial Committee Chair. Mail three copies of full-length papers or abstracts by September 30, 1995 to: H. B. Wilson, Editorial Committee Chair, SECTAM XVIII Department of Engineering Science and Mechanics University of Alabama Box 870278 Tuscaloosa, AL 35487-0278 email: hwilson@ua1vm.ua.edu EDITORIAL COMMITTEE H. B. Wilson, University of Alabama, Chair W. F. Ames, Georgia Institute of Technology R. C. Batra, Virginia Polytechnic Institute and State University C. W. Bert, University of Oklahoma R. A. Schapery, University of Texas at Austin D. S. Stewart, University of Illinois F. F. Swinson, Oak Ridge National Laboratory EXECUTIVE COMMITTEE J. L. Hill, University of Alabama, Chair K. K. Stevens, Florida Atlantic University, Vice Chair H. B. Wilson, University of Alabama, Editorial Committee Chair S. C. Gambrell, Jr., University of Alabama, Secretary/Treasurer T. H. Moulden and B. N. Antar, SECTAM XVI, University of Tennessee Space Institute F. A. Akl, SECTAM XVII, Louisiana Tech University DEADLINES June 30, 1995 Proposals for specially organized technical sessions and/or panel discussions September 30, 1995 Deadline for full-length papers December 30, 1995 Notification of acceptance January 31, 1996 Deadline for camera-ready manuscripts February 15, 1996 Program and conference material mailed to prospective participants March 8, 1996 Deadline for conference rates at hotels April 14-16, 1996 Conference CONFERENCE INFORMATION For technical information, please contact: J. L. Hill, SECTAM XVIII Executive Chair Department of Engineering Science and Mechanics University of Alabama Box 870278, 210 Hardaway Hall Tuscaloosa, AL 35487-0278 Phone: (205) 348-1628 FAX: (205) 348-7240 email: jhill@ua1vm.ua.edu For general information, please contact: Ms. Patty Stewart, SECTAM XVIII University of Alabama Box 870278 Tuscaloosa, AL 35487-0278 Phone: (205) 348-7251 FAX: (205) 348-7240 email: mhdept@ua1vm.ua.edu World Wide Web: http://hamton.eng.ua.edu/college/orgs/esm/sectam.html REGISTRATION FORM SECTAM XVIII, April 14-16, 1996, Tuscaloosa, Alabama Name: ________________________________ Title: __________________________________________ Address _______________________________ ___________________________________________________ City ________________________________ State/Country _______________________ Zip ___________ Telephone _____________ Fax _______________ Email (internet) ___________________________________ PLEASE CHECK APPROPRIATE ITEMS BELOW: Registration fee: _____ $175 early bird or _____ $200 after February 28, 1996 (including the costs of a copy of the proceedings, a banquet, a lunch, and two breakfasts) Author page charge: $17/single-spaced page of camera-ready manuscript Total page charge _________________________ Student registration fee for technical sessions only (meals and proceedings extra): _____ $35 early bird or _____ $45 after February 28, 1996 (Authors of student papers are exempt from page charges.) ______ Amount enclosed: __________________________________ ______ I am interested in the Spouse/Friends Program. Please make check, money order, or draft payable in U.S. currency to: The University of Alabama - SECTAM XVIII Please mail the completed form with payment to: Registration Services College of Continuing Studies University of Alabama Box 870388 Tuscaloosa, AL 35487-0388 Phone in Registration (credit card only): (205) 348-3000 Fax Registration (credit card or purchase order): (205) 348-6614 Fax or phone in registration must have PO # or credit card # and information. If PO # is used, please attach. THE BRYANT CONFERENCE CENTER & HOTEL The Bryant Conference Center will be the site for SECTAM XVIII. The Bryant Conference Center and Sheraton Capstone Inn are located on the campus of the University of Alabama and adjacent to the Paul Bear Bryant Museum. The hotel offers high quality service in a cordial atmosphere with modern comfortable facilities. Room rates per night for the conference are: Single Occupancy: $65.00 Double Occupancy: $75.00 For reservations, please call the Sheraton Capstone Inn (205) 752-3200. The cut-off date for hotel conference rates is March 8, 1996. Alternatively, the newly-constructed Hampton Inn is located less than a mile from campus and may be reached at (205) 553-9800. Room rates per night are: Single Occupancy: $50.00 Double Occupancy: $55.00 Information about other accommodations will be provided with your registration confirmation. TRAVEL INFORMATION Direct airline service to Tuscaloosa, Alabama is available on American Eagle from their hub in Nashville, Tennessee. Most major airlines fly into Birmingham International Airport. Tuscaloosa is a one-hour trip southwest on I20/59 from Birmingham. Car rentals are available at the airport. SPOUSES/FRIENDS PROGRAM Information about the Spouses/Friends Program will be available at registration. Please check the box on the registration form to receive more information on such area attractions as: Mound Archaeological Park and Museum (Native American Archeology, Geology) Historical University Campus Buildings Gulf States Paper Corporation (Guided Tours of a Fabulous Collection of American Art) Scenic Tannehill State Park (Museum, Crafts, Nature Trails, Civil War Iron Works, Water Powered Grist Mill) PLEASE POST OR SHARE WITH OTHERS The University of Alabama is an affirmative action/equal opportunity institution. From lxu@cs.cuhk.hk Mon Sep 11 12:55:33 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 11 Sep 95 12:55:30 -0500; AA04881 Received: from bilby.cs.uwa.oz.au by lucy.cs.wisc.edu; Mon, 11 Sep 95 12:55:26 -0500 Received: from (mafm@parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA02342; Mon, 11 Sep 1995 18:38:27 +0800 Message-Id: <199509111038.SAA02342@cs.uwa.oz.au> From: "Dr. Xu Lei" To: Reinforce@cs.uwa.edu.au Subject: ICONIP96 [connectionists] Date: Mon, 11 Sep 1995 16:46:37 +0800 FIRST CALL FOR PAPERS 1996 INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING The Annual Conference of the Asian Pacific Neural Network Assembly ICONIP'96, September 24 - 27, 1996 Hong Kong Exhibition and Convention Center, Wan Chai, Hong Kong The goal of ICONIP'96 is to provide a forum for researchers and engineers from academia and industry to meet and to exchange ideas on the latest developments in neural information processing. The conference further serves to stimulate local and regional interests in neural information processing and its potential applications to industries indigenous to this region. CONFERENCE TOPICS ================= * Theory * Algorithms & Architectures * Applications * Supervised/Unsupervised Learning * Hardware Implementations * Hybrid Systems * Neurobiological Systems * Associative Memory * Visual & Speech Processing * Intelligent Control & Robotics * Cognitive Science & AI * Recurrent Net & Dynamics * Image Processing * Pattern Recognition * Computer Vision * Time Series Prediction * Financial Engineering * Optimization * Fuzzy Logic * Evolutionary Computing * Other Related Areas CONFERENCE'S SCHEDULE ===================== Submission of paper February 1, 1996 Notification of acceptance May 1, 1996 Early registration deadline July 1, 1996 SUBMISSION INFORMATION ====================== Authors are invited to submit one camera-ready original and five copies of the manuscript written in English on A4-format white paper with one inch margins on all four sides, in one column format, no more than six pages including figures and references, single-spaced, in Times-Roman or similar font of 10 points or larger, and printed on one side of the page only. Electronic or fax submission is not acceptable. Additional pages will be charged at USD $50 per page. Centered at the top of the first page should be the complete title, author(s), affiliation, mailing, and email addresses, followed by an abstract (no more than 150 words) and the text. Each submission should be accompanied by a cover letter indicating the contacting author, affiliation, mailing and email addresses, telephone and fax number, and preference of technical session(s) and format of presentation, either oral or poster (both are published). All submitted papers will be refereed by experts in the field based on quality, clarity, originality, and significance. Authors may also retrieve the ICONIP style, "iconip.tex" and "iconip.sty" files for the conference by anonymous FTP at ftp.cs.cuhk.hk in the directory /pub/iconip96. For further information, inquiries, and paper submissions please contact ICONIP'96 Secretariat Department of Computer Science The Chinese University of Hong Kong Shatin, N.T., Hong Kong Fax (852) 2603-5024 E-mail: iconip96@cs.cuhk.hk http://www.cs.cuhk.hk/iconip96 ====================================================================== General Co-Chairs ================= Omar Wing, CUHK Shun-ichi Amari, Tokyo U. Advisory Committee ================== International ------------- Yaser Abu-Mostafa, Caltech Michael Arbib, U. Southern Cal. Leo Breiman, UC Berkeley Jack Cowan, U. Chicago Rolf Eckmiller, U. Bonn Jerome Friedman, Stanford U. Stephen Grossberg, Boston U. Robert Hecht-Nielsen, HNC Geoffrey Hinton, U. Toronto Anil Jain, Michigan State U. Teuvo Kohonen, Helsinki U. of Tech. Sun-Yuan Kung, Princeton U. Robert Marks, II, U. Washington Thomas Poggio, MIT Harold Szu, US Naval SWC John Taylor, King's College London David Touretzky, CMU C. v. d. Malsburg, Ruhr-U. Bochum David Willshaw, Edinburgh U. Lofti Zadeh, UC Berkeley Asia-Pacific Region ------------------- Marcelo H. Ang Jr, NUS, Singapore Sung-Yang Bang, POSTECH, Pohang Hsin-Chia Fu, NCTU., Hsinchu Toshio Fukuda, Nagoya U., Nagoya Kunihiko Fukushima, Osaka U., Osaka Zhenya He, Southeastern U., Nanjing Marwan Jabri, U. Sydney, Sydney Nikola Kasabov, U. Otago, Dunedin Yousou Wu, Tsinghua U., Beijing Organizing Committee ==================== L.W. Chan (Co-Chair), CUHK K.S. Leung (Co-Chair), CUHK D.Y. Yeung (Finance), HKUST C.K. Ng (Publication), CityUHK A. Wu (Publication), CityUHK K.P. Lam (Publicity), CUHK M.W. Mak (Local Arr.), HKPU C.S. Tong (Local Arr.), HKBU T. Lee (Registration), CUHK M. Stiber (Registration), HKUST K.P. Chan (Tutorial), HKU H.T. Tsui (Industry Liaison), CUHK I. King (Secretary), CUHK Program Committee ================= Co-Chairs --------- Lei Xu, CUHK Michael Jordan, MIT Erkki Oja, Helsinki Univ. of Tech. Mitsuo Kawato, ATR Members ------- Yoshua Bengio, U. Montreal Chris Bishop, Aston U. Leon Bottou, Neuristique Gail Carpenter, Boston U. Laiwan Chan, CUHK Huishen Chi, Peking U. Peter Dayan, MIT Kenji Doya, ATR Scott Fahlman, CMU Francoise Fogelman, SLIGOS Lee Giles, NEC Research Inst. Michael Hasselmo, Harvard U. Kurt Hornik, Technical U. Wien Steven Nowlan, Synaptics Jeng-Neng Hwang, U. Washington Nathan Intrator, Tel-Aviv U. Larry Jackel, AT&T Bell Lab Adam Kowalczyk, Telecom Australia Soo-Young Lee, KAIST Todd Leen, Oregon Grad. Inst. Cheng-Yuan Liou, National Taiwan U. David MacKay, Cavendish Lab Eric Mjolsness, UC San Diego John Moody, Oregon Grad. Inst. Nelson Morgan, ICSI Michael Perrone, IBM Watson Lab Ting-Chuen Pong, HKUST Paul Refenes, London Business School Hava Siegelmann, Technion Ah Chung Tsoi, U. Queensland Benjamin Wah, U. Illinois Andreas Weigend, Colorado U. Ronald Williams, Northeastern U. John Wyatt, MIT Alan Yuille, Harvard U. Richard Zemel, CMU From cohn@psyche.mit.edu Mon Sep 11 23:16:47 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Mon, 11 Sep 95 23:16:45 -0500; AA12507 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Mon, 11 Sep 95 23:16:43 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa15747; 11 Sep 95 22:09:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa15742; 11 Sep 95 21:59:45 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa27806; 11 Sep 95 21:59:24 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa18831; 11 Sep 95 18:07:49 EDT Received: from PSYCHE.MIT.EDU by CS.CMU.EDU id aa04520; 11 Sep 95 18:06:51 EDT Received: by psyche.mit.edu (4.1/DA1.0.4) id AA20429; Mon, 11 Sep 95 18:06:41 EDT Date: Mon, 11 Sep 95 18:06:41 EDT From: David Cohn Message-Id: <9509112206.AA20429@psyche.mit.edu> To: connectionists@cs.cmu.edu Subject: NIPS*95 Registration Info Available [As always, apologies to those who, by dint of subscribing to overlapping multiple mailing lists, receive multiple copies of this announcement.] CONFERENCE ANNOUNCEMENT Neural Information Processing Systems Natural and Synthetic Monday, Nov. 27 - Saturday, Dec. 2, 1995 Denver, Colorado http://www.cs.cmu.edu/Web/Groups/NIPS/NIPS.html This is the ninth meeting of an interdisciplinary conference which brings together neuroscientists, engineers, computer scientists, cognitive scientists, physicists, and mathematicians interested in all aspects of neural processing and computation. The confer- ence will include invited talks, and oral and poster presenta- tions of refereed papers. There will be no parallel sessions. There will also be one day of tutorial presentations (Nov. 27) preceding the regular session, and two days of focused workshops will follow at a nearby ski area (Dec. 1-2). Major conference topics include: Neuroscience, Theory, Implemen- tations, Applications, Algorithms & Architectures, Visual Pro- cessing, Speech/Handwriting/Signal Processing, Cognitive Science & AI, Control, Navigation and Planning. Detailed information and registration materials are available electronically at http://www.cs.cmu.edu/Web/Groups/NIPS/NIPS.html ftp://psyche.mit.edu/pub/NIPS95/ Students who require financial support to attend the conference are urged to retrieve a copy of the registration brochure as soon as possible in order to meet the aid application deadline. Mail general inquiries/requests for registration material to: NIPS*95 Registration Dept. of Mathematical and Computer Sciences Colorado School of Mines Golden, CO 80401 USA FAX: (303) 273-3875 e-mail: nips95@mines.colorado.edu From kim.plunkett@psy.ox.ac.uk Wed Sep 13 15:38:32 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Wed, 13 Sep 95 15:38:29 -0500; AA14544 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Wed, 13 Sep 95 15:38:24 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17675; 13 Sep 95 11:48:41 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17673; 13 Sep 95 11:20:35 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa29582; 13 Sep 95 11:19:30 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa17160; 13 Sep 95 10:12:25 EDT Received: from oxmail.ox.ac.uk by CS.CMU.EDU id aa20868; 13 Sep 95 10:08:07 EDT Received: from ep2.psych.ox.ac.uk by oxmail.ox.ac.uk. with SMTP (PP) id <10445-0@oxmail.ox.ac.uk.>; Wed, 13 Sep 1995 15:07:53 +0100 Received: from EP2_PSYCH/SpoolDir by ep2.psych.ox.ac.uk (Mercury 1.21); 13 Sep 95 15:05:25 +0000 Received: from SpoolDir by EP2_PSYCH (Mercury 1.21); 13 Sep 95 15:05:19 +0000 Received: from mac17.psych.ox.ac.uk by ep2.psych.ox.ac.uk (Mercury 1.21); 13 Sep 95 15:05:13 +0000 X-Mailer: InterCon TCP/Connect II 1.2.1 Message-Id: <9509131505.AA53353@mac17.psych.ox.ac.uk> Date: Wed, 13 Sep 1995 15:05:53 +0000 From: Kim Plunkett To: connectionists@cs.cmu.edu, DEV-EUROPE@durham.ac.uk, info-childes@poppy.PSY.CMU.EDU, psyling@psy.gla.ac.uk Subject: Special Issue of LCP Manuscript submissions are invited for inclusion in a Special Issue of the journal "Language and Cognitive Processes" on Connectionist Approaches to Language Development. It is anticipated that most of the papers in the special issue will describe previously unpublished work on some aspect of language development (first or second language learning in either normal or disordered populations) that incorporates a neural network modelling component. However, theoretical papers discussing the general enterprise of connectionist modelling within the domain of language development are also welcome. The deadline for submissions is 1st April 1996. Manuscripts should be sent to the guest editor for this special issue: Kim Plunkett, Department of Experimental Psychology, Oxford University, South Parks Road, Oxford, OX1 3UD, UK (email: plunkett@psy.ox.ac.uk FAX: 1865-310447). All manuscripts will be submitted to the usual Language and Cognitive Processes peer review process. From antsakli@maddog.ee.nd.edu Fri Sep 15 12:07:39 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 15 Sep 95 12:07:35 -0500; AA22086 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 15 Sep 95 12:07:33 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19763; 15 Sep 95 10:39:40 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19761; 15 Sep 95 10:14:24 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01131; 15 Sep 95 10:14:12 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa10374; 14 Sep 95 17:35:50 EDT Received: from maddog.ee.nd.edu by EDRC.CMU.EDU id aa05743; 14 Sep 95 17:35:22 EDT Received: (from antsakli@localhost) by maddog.ee.nd.edu (8.6.12/8.6.12) id QAA15701 for connectionists@cs.cmu.edu; Thu, 14 Sep 1995 16:35:17 -0500 Date: Thu, 14 Sep 1995 16:35:17 -0500 From: Panos Antsaklis Message-Id: <199509142135.QAA15701@maddog.ee.nd.edu> To: connectionists@cs.cmu.edu Subject: Paper available: "The Dependence Identification Neural Network Construction Algorithm FTP-host: rottweiler.ee.nd.edu FTP-filename: /pub/isis/tnn1845.ps.gz The following paper is available by anonymous ftp. It will appear in an upcoming issue of the IEEE Transactions on Neural Networks. ------------------------------------------------------------------------ THE DEPENDENCE IDENTIFICATION NEURAL NETWORK CONSTRUCTION ALGORITHM John O. Moody and Panos J. Antsaklis Dept. of Electrical Engineering University of Notre Dame Notre Dame, IN 46556, USA email: jmoody@maddog.ee.nd.edu (Accepted for publication in the IEEE Transactions on Neural Networks) Abstract An algorithm for constructing and training multilayer neural networks, dependence identification, is presented in this paper. Its distinctive features are that (i) it transforms the training problem into a set of quadratic optimization problems that are solved by a number of linear equations, (ii) it constructs an appropriate network to meet the training specifications, and (iii) the resulting network architecture and weights can be further refined with standard training algorithms, like backpropagation, giving a significant speed-up in the development time of the neural network and decreasing the amount of trial and error usually associated with network development. -------------------------------------------------------------------- ftp instructions: unix% ftp rottweiler.ee.nd.edu Name: anonymous password: your email address ftp> cd pub/isis ftp> binary ftp> get tnn1845.ps.gz ftp> bye unix% gzip -d tnn1845.ps.gz unix% lpr tnn1845.ps -------------------------------------------------------------------- From caruana+@cs.cmu.edu Fri Sep 15 23:04:14 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Fri, 15 Sep 95 23:04:11 -0500; AA29676 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Fri, 15 Sep 95 23:04:07 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19807; 15 Sep 95 10:49:50 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19765; 15 Sep 95 10:15:14 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01137; 15 Sep 95 10:14:25 EDT Received: from GS79.SP.CS.CMU.EDU by B.GP.CS.CMU.EDU id aa18472; 15 Sep 95 9:23:50 EDT Received: from GS79.SP.CS.CMU.EDU by GS79.SP.CS.CMU.EDU id aa29913; 15 Sep 95 9:23:34 EDT To: Connectionists@cs.cmu.edu Subject: NIPS*95 Workshop: Call for Participation From: Rich Caruana Date: Fri, 15 Sep 95 09:23:26 -0400 Message-Id: <29911.811171406@GS79.SP.CS.CMU.EDU> Sender: Richard_Caruana@GS79.SP.CS.CMU.EDU *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* *-* POST-NIPS*95 WORKSHOP *-* *-* December 1-2, 1995 *-* *-* Vail, Colorado *-* *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* *-* CALL FOR PARTICIPATION *-* *-*-*-*-*-*-*-*-*-*-*-*-*-*-*-* TITLE: "Learning to Learn: Knowledge Consolidation and Transfer in Inductive Systems" ORGANIZERS: Jon Baxter, Rich Caruana, Tom Mitchell, Lori Pratt, Danny Silver, Sebastian Thrun. INVITED TALKS BY: Leo Breiman (Stanford, undecided) Tom Mitchell (CMU) Tomaso Poggio (MIT) Noel Sharkey (Sheffield) Jude Shavlik (Wisconsin) WEB PAGES (for more information): Our Workshop: http://www.cs.cmu.edu/afs/cs/usr/caruana/pub/transfer.html NIPS*95 Info: http://www.cs.cmu.edu/afs/cs/project/cnbc/nips/NIPS.html WORKSHOP DESCRIPTION: The power of tabula rasa learning is limited. Because of this, interest is increasing in methods that capitalize on previously acquired domain knowledge. Examples of these methods include: o using symbolic domain theories to bias connectionist networks o using unsupervised learning on a large corpus of unlabelled data to learn features useful for subsequent supervised learning on a smaller labelled corpus o using models previously learned for other problems as a bias when learning new, but related, problems o using extra outputs on a connectionist network to bias the hidden layer representation towards more predictive features There are many different approaches: hints, knowledge-based artificial neural nets (KBANN), explanation-based neural nets (EBNN), multitask learning (MTL), knowledge consolidation, etc. What they all have in common is the attempt to transfer knowledge from other sources to benefit the current inductive task. The goal of this workshop is to provide an opportunity for researchers and practitioners to discuss problems and progress in knowledge transfer in learning. We hope to identify research directions, debate different theories and approaches, discover unifying principles, and begin to start answering questions like: o when will transfer help -- or hinder? o what should be transferred? o how should it be transferred? o what are the benefits? o in what domains is transfer most useful? SUBMISSIONS: We solicit presentations from anyone working in (or near): o Sequential/incremental, compositional (learning by parts), and parallel learning o Task knowledge transfer (symbolic-neural, neural-neural) o Adaptation of learning algorithms based on prior learning o Learning domain-specific inductive bias o Combining predictions made for related tasks from one domain o Combining supervised learning (where the goal is to learn one feature from the other features) with unsupervised learning (where the goal is to learn every feature from all the other features) o Combining symbolic and connectionist methods via transfer o Fundamental problems/issues in learning to learn o Theoretical models of learning to learn o Cognitive models of, or evidence for, transfer in learning Please send a short (one page or less) description of what you want to present to one of the co-chairs below by Oct 15. Email is preferred. We'll select from the submissions and publish a workshop schedule by Nov 1. Preference will be given to submissions that are likely to generate debate and that go beyond summarizing prior published work by raising important issues or suggesting directions for future work. Suggestions for moderator or panel-led discussions (e.g., sequential vs. parallel transfer) are also encouraged. We plan to run the workshop as a workshop, not as a mini conference, so be daring! We look forward to your submission. Rich Caruana Daniel L. Silver School of Computer Science Department of Computer Science Carnegie Mellon University Middlesex College 5000 Forbes Avenue University of Western Ontario Pittsburgh, PA 15213, USA London, Ontario, Canada N6A 3K7 email: caruana@cs.cmu.edu email: dsilver@csd.uwo.ca ph: (412) 268-3043 ph: (519) 473-6168 fax: (412) 268-5576 fax: (519) 661-3515 See you in Colorado! From william.beaudot@csemne.ch Sat Sep 16 16:35:39 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 16 Sep 95 16:35:36 -0500; AA08128 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 16 Sep 95 16:35:32 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab20945; 16 Sep 95 3:57:15 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab20943; 16 Sep 95 3:43:17 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01506; 16 Sep 95 3:43:01 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa22909; 15 Sep 95 13:44:43 EDT Received: from design.csemne.ch by RI.CMU.EDU id aa01349; 15 Sep 95 13:44:08 EDT Received: from rotie.csemne.ch by morgon.csemne.ch; Fri, 15 Sep 1995 19:41:47 +0200 Received: by rotie.csemne.ch; Fri, 15 Sep 1995 19:41:46 +0200 Date: Fri, 15 Sep 1995 19:41:46 +0200 From: william.beaudot@csemne.ch Message-Id: <199509151741.TAA13120@rotie.csemne.ch> To: Connectionists@cs.cmu.edu Subject: Winter Retina Conference '96 Cc: Vision-List@TELEOS.COM, frog-net@rana.usc.edu, comp-neuro@smaug.bbb.caltech.edu, cogneuro@ptolemy-ethernet.arc.nasa.gov, neuron-request@CATTELL20.psych.upenn.edu The first annual "Winter Retina Conference: Physiology, Computation, and Neuromorphic Engineering for Vision" will be held in Jackson Hole, Wyoming, USA from 16-20 January 1996. The meeting will bring together leaders in the fields of the physiology, computation and engineering of early vision in vertebrates and invertebrates. The meeting is limited to 50 participants with the intention of fostering rich interaction accross the fields. For more info please see our WWW home page at URL: http://shi18.uth.tmc.edu/retcon.htm The meeting is being organized by: Greg Maguire and Harvey Karten in the USA, and William Beaudot and Andre vanSchaik in Switzerland. ------------------------------------------------------------------------------ For those who have not access to Internet, here is the text version of the WWW home page for the announcement: WINTER RETINA CONFERENCE '96 Physiology, Computation, and Neuromorphic Engineering for Vision 16-20 January 1996 Jackson Hole, Wyoming, USA First Anouncement and Call For Abstracts ======================================== In January 1996, the first annual Winter Retina Conference will be held in Jackson Hole, Wyoming, USA. The meeting will bring together leaders in the field of neural circuitry, computational modeling, and neuromorphic engineering in retinas, including both vertebrate and invertebrates. The purpose of the Winter Retina Conference is to present the latest results in the fundamental aspects of retinal circuitry in a setting conducive to informal and rich interaction between the participants. The meeting is limited to 50 participants and participation is by application and acceptance only. The conference will include daily lectures and demonstrations. SUN Ultra-SPARC and Super-SPARC workstations will be available for demonstrations. Conference Site: Teton Village, Jackson Hole, Wyoming ===================================================== Jackson Hole is a sun drenched, mountain-rimmed valley noted for its natural, rugged beauty, powder snow, and numerous ski slopes. Many other activities besides great downhill skiing are available, including: X-country skiing, ice-skating, sleigh rides, fishing, hunting, hiking, hot spring soaking, and horseback riding to name a few. Teton Village will be the host site for the conference. Restaurants, niteclubs, and shopping abound here. Yellowstone and Grand Teton National Parks are a short drive away from the slopes. Moutain climbing schools and guides are available in the city. Conference Hotel: ================= The Inn at Jackson Hole. A beautiful hotel at the base of the ski slope (yep, ski-in and ski-out) and in the midst of Teton Village. Everything you need is in walking distance of the hotel, including good restaurants and shopping. Standard room (2 beds)- $80.00/ night; Deluxe room (kitchenette)-$120.00/night; Loft suites- $150.00/night. Reservations at 800-842-7666 or fax at307-733-0844. Identify yourself as an attendee to the Winter Retina Conference for these special rates. Travel: ======= Jackson Hole is served by American, United, and Delta Airlines. A 5-10% discount, depending on class of service, is available on American Airlines, the official airline of the 1996 Winter Retina Conference. We advise using American Airlines because they provide the only jet service directly to Jackson Hole. To receive a 5-10% discount on American Airlines, please call American Airlines Meeting Services desk at 1-800-433-1790, identify youself as an attendee to the Winter Retina Conference, and use American Airlines "star number S-0116HZ" to book your flight. FEE: Upon Acceptance a Registration Fee of $100 US ================================================== Housing and travel information will be sent following acceptance. Application: Send a one page abstract and a short c.v. to either: ================================================================= Winter Retina Conference, Greg Maguire, Department of Neurobiology & Anatomy, University of Texas, 6420 Lamar Fleming, Houston, TX 77030, USA or Winter Retina Conference, William Beaudot, Centre Suisse d'Electronique et de Microtechnique SA, IC & Systems Research, Dept. of Bio-Inspired Advanced Research, Maladiere 71, Case postale 41, CH-2007 Neuchatel, Switzerland or Winter Retina Conference, Andre'van Schaik, EPFL-MANTRA Centre for Neuro-Mimetic Systems INJ-035 Ecublens, CH-1015 Lausanne, Switzerland Information and abstracts may also be sent via email: gmaguire@gsbs.gs.uth.tmc.edu Confirmed Attendees =================== Xavier Arreguit, CSEM, Switzerland; William Beaudot, CSEM, Switzerland; Horacio Cantiello, Harvard; Nicolas Franceschini, CNRS, Marseille; Jeanny Herault, Grenoble, France; Harvey Karten, UCSD; Kent Keyser, UCSD; Greg Maguire, Texas; Misha Mahowald, Oxford; Steve Massey, Texas; Haluk Ogmen, Houston; Peter Sterling, Pennsylvania; Andre van Schaik, Lausanne, Switzerland; Frank Werblin, Berkeley Organizing Committee: ===================== William Beaudot, CSEM, Switzerland Harvey Karten, UCSD, USA Greg Maguire, Texas, USA Andre van Schaik, EPFL, Switzerland Registration Form ================= A receipt, program, and information package will be mailed to participants following registration payment. Please include a check for $100 (USA) made payable to: Winter Retina Conference. The fee includes participation in the daily meetings, a social event, and an official t-shirt. Send form and payment by snail mail to: --------------------------------------- Greg Maguire Sensory Sciences Center University of Texas 6420 Lamar Fleming Houston, TX 77030 USA Name: ----- Institution: ------------ Address: -------- Email: ------ Telephone: ---------- Fax: ---- From jagota@ponder.csci.unt.edu Sat Sep 16 16:35:41 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 16 Sep 95 16:35:38 -0500; AA08134 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 16 Sep 95 16:35:35 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa20961; 16 Sep 95 4:06:07 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa20947; 16 Sep 95 3:44:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01512; 16 Sep 95 3:43:36 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa28478; 15 Sep 95 19:33:14 EDT Received: from ponder.csci.unt.edu by EDRC.CMU.EDU id aa10945; 15 Sep 95 19:32:56 EDT Received: by ponder (5.61/1.36) id AA01789; Fri, 15 Sep 95 18:33:34 -0500 Date: Fri, 15 Sep 95 18:33:34 -0500 From: Jagota Arun Kumar Message-Id: <9509152333.AA01789@ponder> To: connectionists@cs.cmu.edu Subject: Abstract: NN Optimization on Compressible Graphs Dear Connectionists: I announce a cleaner version of a paper I announced back in 1992. It is essentially unchanged in other aspects. ------------------------------------------------------------------------ Performance of Neural Network Algorithms for Maximum Clique On Highly Compressible Graphs Arun K. Jagota and Kenneth W. Regan The problem of finding the size of the largest clique in an undirected graph is NP-hard, even to approximate well. Simple algorithms work quite well however on random graphs. It is felt by many, however, that the uniform distribution u(n) does not accurately reflect the nature of instances that come up in practice. It is argued that when the actual distribution is unknown, it is more appropriate to suppose that instances come from the Solomonof-Levin or universal distribution m(x) instead, which assigns higher weight to instances with shorter descriptions. Because m(x) is neither computable nor samplable, we employ a realistic analogue q(x) which lends itself to efficient empirical testing. We experimentally evaluate how well certain neural network algorithms for Maximum Clique perform on graphs drawn from q(x), as compared to those drawn from u(n). The experimental results are as follows. All nine algorithms we evaluated performed roughly equally-well on u(n), whereas three of them---the simplest ones---performed markedly poorer than the other six on q(x). Our results suggest that q(x), while postulated as a more realistic distribution to test the performance of algorithms than u(n), is also one that discriminates their performance better. Our q(x) sampler can be used to generate compressible instances of any discrete problem. ------------------------------------------------------------------------ Send requests by e-mail to jagota@cs.unt.edu I use this mechanism to get some indication of the amount of interest, if any, there is in this type of work. Arun Jagota From A.Sharkey@dcs.shef.ac.uk Sat Sep 16 22:04:55 1995 Received: from lucy.cs.wisc.edu by sea.cs.wisc.edu; Sat, 16 Sep 95 22:04:53 -0500; AA09341 Received: from TELNET-1.SRV.CS.CMU.EDU by lucy.cs.wisc.edu; Sat, 16 Sep 95 22:04:50 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa20945; 16 Sep 95 3:55:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa20943; 16 Sep 95 3:43:14 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa01501; 16 Sep 95 3:42:46 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa20605; 15 Sep 95 11:41:27 EDT Received: from gw.dcs.shef.ac.uk by CS.CMU.EDU id aa13362; 15 Sep 95 11:40:18 EDT Received: from entropy.dcs.shef.ac.uk by dcs.shef.ac.uk (4.1/DAVE-1.0) id AA15145; Fri, 15 Sep 95 16:40:02 BST Received: by entropy.dcs.shef.ac.uk (920330.SGI/SMI-4.1) id AA29776; Fri, 15 Sep 95 16:40:21 +0100 Date: Fri, 15 Sep 95 16:40:21 +0100 From: A.Sharkey@dcs.shef.ac.uk Message-Id: <9509151540.AA29776@entropy.dcs.shef.ac.uk> To: Connectionists@cs.cmu.edu Subject: SPECIAL ISSUE of Connection Science PRELIMINARY CALL FOR PAPERS: Deadline February 14th 1996 ************ COMBINING NEURAL NETS ************ A special issue of Connection Science Papers are sought for this special issue of Connection Science. The aim of this special issue is to examine when, how, and why neural nets should be combined. The reliability of neural nets can be increased through the use of both redundant and modular nets, (either trained on the same task under differing conditions, or on different subcomponents of a task). Questions about the exploitation of redundancy and modularity in the combination of nets, or estimators, have both an engineering and a biological relevance, and include the following: * how best to combine the outputs of several nets. * quantification of the benefits of combining. * how best to create redundant nets that generalise differently (e.g. active learning methods) * how to effectively subdivide a task. * communication between neural net modules. * increasing the reliability of nets. * the use of neural nets for safety critical applications. Special issue editor: Amanda Sharkey (Sheffield, UK) Editorial Board: Leo Breiman (Berkeley, USA) Nathan Intrator (Brown, USA) Robert Jacobs (Rochester, USA) Michael Jordan (MIT, USA) Paul Munro (Pittsburgh, USA) Michael Perrone (IBM, USA) David Wolpert (Santa Fe Institute, USA) We solicit either theoretical or experimental papers on this topic. Questions and submissions concerning this special issue should be sent by February 14th 1996 to: Dr Amanda Sharkey, Department of Computer Science, Regent Court, Portobello Street, University of Sheffield, Sheffield, S1 4DP, United Kingdom. Net: amanda@dcs.shef.ac.uk