From biehl@physik.uni-wuerzburg.de Mon Oct 14 16:08:09 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA06301 for ; Mon, 14 Oct 1996 16:08:03 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id QAA00447 for ; Mon, 14 Oct 1996 16:08:00 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17791; 14 Oct 96 14:35:44 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17789; 14 Oct 96 14:09:58 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05312; 14 Oct 96 14:09:33 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa08902; 14 Oct 96 7:03:28 EDT Received: from wptx01.physik.uni-wuerzburg.de by EDRC.CMU.EDU id aa04687; 14 Oct 96 7:03:02 EDT Received: (from smap@localhost) by wptx01.physik.uni-wuerzburg.de (8.7.5/8.7.3/TPhys_S) id NAA05442 for ; Mon, 14 Oct 1996 13:02:34 +0200 (MESZ) From: Michael Biehl Received: from wptx08.physik.uni-wuerzburg.de(132.187.40.8) by wptx01.physik.uni-wuerzburg.de (smap V1.3) id sma005440 for ; Mon Oct 14 13:02:30 1996 Received: (from biehl@localhost) by wptx08.physik.uni-wuerzburg.de (8.7.5/8.7.3/TPhys_C) id NAA18288 for Connectionists@cs.cmu.edu; Mon, 14 Oct 1996 13:02:30 +0200 (MESZ) Message-Id: <199610141102.NAA18288@wptx08.physik.uni-wuerzburg.de> Subject: paper available: Noise Robustness in Multilayer Neural Networks To: Connectionists Date: Mon, 14 Oct 1996 13:02:29 +0200 (MESZ) X-Mailer: ELM [version 2.4 PL24 ME8b] MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit FTP-host: ftp.physik.uni-wuerzburg.de FTP-filename: /pub/preprint/1996/WUE-ITP-96-022.ps.gz The following manuscript is now available via anonymous ftp: (See below for the retrieval procedure) ------------------------------------------------------------------ "Noise Robustness in Multilayer Neural Networks" M. Copelli, R. Eichhorn, O. Kinouchi, M. Biehl, R. Simonetti, P. Riegler, and N. Caticha Ref. WUE-ITP-96-022 Abstract The training of multilayered neural networks in the presence of different types of noise is studied. We consider the learning of realizable rules in nonover- lapping architectures. Achieving optimal generalization depends on knowledge of the noise level, however its misestimation may lead to partial or complete loss of the generalization ability. We demonstrate this effect in the framework of online learning and present the results in terms of noise robustness phase diagrams. While for additive (weight) noise the robustness properties depend on the architecture and size of the networks, this is not so for multiplicative (output) noise. In this case we find a universal behaviour independent of the machine size for both the tree parity and committee machines. --------------------------------------------------------------------- Retrieval procedure: unix> ftp ftp.physik.uni-wuerzburg.de Name: anonymous Password: {your e-mail address} ftp> cd pub/preprint/1996 ftp> get WUE-ITP-96-022.ps.gz (*) ftp> quit unix> gunzip WUE-ITP-96-022.ps.gz e.g. unix> lp WUE-ITP-96-022.ps [8 pages] (*) can be replaced by "get WUE-ITP-96-022.ps". The file will then be uncompressed before transmission (slow!). _____________________________________________________________________ -- Michael Biehl Institut fuer Theoretische Physik Julius-Maximilians-Universitaet Wuerzburg Am Hubland D-97074 Wuerzburg email: biehl@physik.uni-wuerzburg.de homepage: http://www.physik.uni-wuerzburg.de/~biehl Tel.: (+49) (0)931 888 5865 " " " 5131 Fax : (+49) (0)931 888 5141 From anderson@CS.ColoState.EDU Mon Oct 14 16:08:16 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA06307 for ; Mon, 14 Oct 1996 16:08:08 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id QAA00457 for ; Mon, 14 Oct 1996 16:08:06 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17853; 14 Oct 96 14:56:43 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17836; 14 Oct 96 14:41:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05382; 14 Oct 96 14:41:00 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa15545; 14 Oct 96 14:37:22 EDT Received: from clapton.cs.colostate.edu by CS.CMU.EDU id aa01249; 14 Oct 96 14:36:51 EDT Received: (from anderson@localhost) by clapton.cs.colostate.edu (8.7.1/8.7.1) id MAA03873; Mon, 14 Oct 1996 12:36:41 -0600 (MDT) Date: Mon, 14 Oct 1996 12:36:41 -0600 (MDT) Message-Id: <199610141836.MAA03873@clapton.cs.colostate.edu> From: Chuck Anderson To: connectionists@cs.cmu.edu Subject: research assistantship for Spring, 97 The Department of Computer Science at Colorado State University, Fort Collins, CO, is looking for a Masters or Ph.D. student to fill a vacant research assistantship position funded by this NSF project: National Science Foundation, MIP-9628770, 8/96--7/99, PIs: T. Chen, Electrical Engineering, and A. von Mayrhauser and C. Anderson, Computer Science, "Behavioral Level Design Verifications Using Software Testing Techniques and Neural Networks" We plan to use network inversion and methods from optimal experiment design to guide the search for test inputs for complex software systems and hardware models coded in VHDL. We would like a student with a strong background in neural networks, experience with compiler design, and an interest in software and hardware testing. You can learn more about our department at http://www.cs.colostate.edu and about the PIs' research projects at http://www.lance.colostate.edu/depts/ee/Profiles/chen.html http://www.cs.colostate.edu/casi/avm/ http://www.cs.colostate.edu/~anderson To qualify for this position, you must be accepted into the Computer Science graduate program at CSU. You may obtain application material by sending a request via e-mail to gradinfo@cs.colostate.edu. You may also send your resume or questions via e-mail to anderson@cs.colostate.edu. Chuck Anderson anderson@cs.colostate.edu Department of Computer Science http://www.cs.colostate.edu/~anderson Colorado State University office: 970-491-7491 Fort Collins, CO 80523-1873 FAX: 970-491-2466 From ted@SPENCER.CTAN.YALE.EDU Mon Oct 14 16:08:19 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id QAA06304 for ; Mon, 14 Oct 1996 16:08:07 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id QAA00452 for ; Mon, 14 Oct 1996 16:08:02 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa17817; 14 Oct 96 14:47:05 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa17793; 14 Oct 96 14:10:56 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05323; 14 Oct 96 14:10:10 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa15037; 14 Oct 96 14:06:04 EDT Received: from SPENCER.CTAN.YALE.EDU by RI.CMU.EDU id aa27486; 14 Oct 96 14:05:34 EDT Received: from PLANCK.CTAN.YALE.EDU by SPENCER.CTAN.YALE.EDU via ESMTP; Mon, 14 Oct 1996 18:05:18 GMT Received: by PLANCK.CTAN.YALE.EDU (Sendmail-8.7.1/res.nnc.client.cf-3.6) id SAA13101; Mon, 14 Oct 1996 18:05:17 GMT Date: Mon, 14 Oct 1996 18:05:17 GMT From: ted@SPENCER.CTAN.YALE.EDU Message-Id: <199610141805.SAA13101@PLANCK.CTAN.YALE.EDU> To: connectionists@cs.cmu.edu CC: ted@SPENCER.CTAN.YALE.EDU, ktsai@student.med.harvard.edu, hines@SPENCER.CTAN.YALE.EDU Subject: The Electrotonic Workbench For those who are concerned with how electrical signals spread in biological neurons, it may be of interest to learn that Michael Hines's simulation program NEURON can now compute the electrotonic transform and display the results as neuromorphic or Log A vs. x renderings at the click of a button. An abstract that presents the basic concepts and illustrates this new feature is at http://www.neuron.yale.edu/papers/ebench/ebench.html Further information about this powerful suite of analytical tools will be presented at the Society for Neuroscience Meeting in Washington, DC on Wednesday, Nov. 20, 1996 at 1 PM (Carnevale, N.T., Tsai, K.Y., and Hines, M.L.. The Electrotonic Workbench. Society for Neuroscience Abstracts 22:1741, 1996, abstract 687.1) This and other references of interest to those who are concerned with biologically realistic neural computation are located at http://www.neuron.yale.edu/papers/nrnrefs.html --Ted From dfisher@vuse.vanderbilt.edu Tue Oct 15 02:00:50 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA11956 for ; Tue, 15 Oct 1996 02:00:40 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id CAA07503 for ; Tue, 15 Oct 1996 02:00:37 -0500 Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id MAA00190; Tue, 15 Oct 1996 12:31:52 +0800 Message-Id: <199610150431.MAA00190@cs.uwa.oz.au> From: dfisher@vuse.vanderbilt.edu (Douglas H. Fisher) To: Connectionists@cs.cmu.edu, bayes-news@stat.cmu.edu, cogpsy@neuro.psy.soton.ac.uk, colt@cs.uiuc.edu, dfisher@vuse.vanderbilt.edu, dietmar@cognition.iig.uni-freiburg.de, genetic-programming@cs.stanford.edu, hybrid-list@cs.ua.edu, ilpnet@IJS.si, kdd@gte.com, ml@ics.uci.edu, mlnet@swi.psy.uva.nl, news-announce-conferences@uunet.uu.net, reinforce@cs.uwa.edu.au, sigart@vaxa.isi.edu, uai@maillist.cs.orst.edu Subject: CFP: 14th International Conference on Machine Learning [connectionists] Date: Mon, 14 Oct 96 15:36:05 CDT Preliminary Call for Papers THE FOURTEENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING July 8-12, 1997 Nashville, Tennessee, USA The Fourteenth International Conference on Machine Learning (ICML-97) will be held at Vanderbilt University in Nashville, Tennessee from July 8 to July 12, 1997. ICML-97 is co-located with the Tenth Annual Conference on Computational Learning Theory (COLT-97), and the organizers anticipate fruitful interactions between the two communities. The ICML-97 program proper includes a half day of tutorials on July 8 (organized in conjunction with COLT-97), a technical program that runs from July 9 through July 11, and a day of workshops on July 12. Submissions are invited that describe empirical, theoretical, and cognitive modeling research in all areas of machine learning. In addition, papers from related disciplines (e.g., information retrieval, statistics, pattern recognition) that deal with adaptive intelligence, (semi-)automated knowledge acquisition, or (semi-)automated knowledge organization are welcome. Submissions that describe the application of machine learning methods to real-world problems are encouraged, but such submissions should speak to general issues of machine learning, perhaps illustrating novel learning methods or demonstrating the utility of established methods in previously unexplored settings. Authors must submit 4 hardcopies of their submissions, as well as a copy of their title page via electronic mail. The mailing addresses for hardcopies are: **Regular Mail** **Express Mail** Doug Fisher/ICML-97 Doug Fisher/ICML-97 Department of Computer Science Department of Computer Science Box 1679, Station B 1500 21st Ave. South Vanderbilt University Room 433, Village at Vanderbilt Nashville, TN 37235 USA Nashville, TN 37212 USA 615-322-2796 (Express mail forms) Submissions must arrive by **January 22, 1997.** Acceptance decisions will be mailed by **March 24, 1997.** Camera-ready copies will be due by **April 18, 1997.** A copy of the title page should be sent via electronic mail to icml97@vuse.vanderbilt.edu by **January 20, 1997** (note the date). The title page should accompany each hardcopy submission, in addition to being sent through electronic mail. The title page, both the electronic and hardcopy versions, should be formatted as follows: Title: Author(s) with address(es): Abstract (200 word maximum): Keywords: Email address of contact author: Phone number of contact author: Multiple submission statement (if applicable): The title page should be detachable from the main body of the paper. The main body should include the paper's title and abstract, but not the authors, keywords, or contact information. The main body (excluding detachable title page, but including everything else such as title, abstract, figures, tables, and references) of a submission must not exceed **16** pages formatted as follows: 12 point font, single-spaced (Baselineskip = 0.1875 inches or 0.4763 cm), a maximum per-page text width of 5.5 inches (14.00 cm), and a maximum per-page text height of 7.5in (19 cm). If the Chair believes that a submission exceeds 660 square inches or 4258 square centimeters (under 12pt, single space assumptions), then the submission will be rejected without review, and an explanation will be provided to the author(s). Submissions with text on both sides of each page are encouraged. For complete submission requirements, as well as information on registration, housing, workshops, and tutorials, see http://cswww.vuse.vanderbilt.edu/~mlccolt/icml97/index.html or send email to icml97@vuse.vanderbilt.edu. From dwang@cis.ohio-state.edu Tue Oct 15 07:35:30 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id HAA13765 for ; Tue, 15 Oct 1996 07:35:20 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id HAA09393 for ; Tue, 15 Oct 1996 07:35:18 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab17791; 14 Oct 96 14:36:55 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab17789; 14 Oct 96 14:09:59 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa05317; 14 Oct 96 14:09:41 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa14278; 14 Oct 96 13:22:31 EDT Received: from mail.cis.ohio-state.edu by RI.CMU.EDU id aa27209; 14 Oct 96 13:22:06 EDT Received: from sarajevo.cis.ohio-state.edu (sarajevo.cis.ohio-state.edu [164.107.136.9]) by mail.cis.ohio-state.edu (8.6.7/8.6.4) with ESMTP id JAA13902; Mon, 14 Oct 1996 09:43:48 -0400 From: DeLiang Wang Received: (dwang@localhost) by sarajevo.cis.ohio-state.edu (8.6.7/8.6.4) id JAA28477; Mon, 14 Oct 1996 09:43:47 -0400 Date: Mon, 14 Oct 1996 09:43:47 -0400 Message-Id: <199610141343.JAA28477@sarajevo.cis.ohio-state.edu> To: connectionists@cs.cmu.edu Subject: Special Issue on Radial Basis Functions Networks Cc: Y.CAMPFENS@elsevier.nl Call for Papers Special Issue on Radial Basis Functions Networks for the journal NEUROCOMPUTING (http://www.elsevier.nl/locate/neucom) -------------------------------------------------------------------- One of the most popular neural network architectures due to their fast learning and broad range of applicability are the Radial Basis Functions (RBF) Networks. This special issue is dedicated to recent advances in all aspects of this type of architecture, including but not restricted to: * theoretical contributions, * learning methods: supervised, unsupervised, on-line, etc., * architectural enhancements, * applications in signal procession, vision, control, etc., * comparative assessments to other neural network architectures. Submit 6 copies of your manuscript (including keywords, biosketch of all authors, email address of corresponding author) to: V. David Sanchez A. Neurocomputing - Editor in Chief - Nova Southeastern University School of Computer and Information Sciences 3100 SW 9th Avenue Fort Lauderdale, FL 33315 U.S.A. Fax +1 (954) 723-2744 Email dsanchez@scis.nova.edu Deadline: 15 December 1996 -------------------------------------------------------------------- From zador@salk.edu Tue Oct 15 17:55:57 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA28340 for ; Tue, 15 Oct 1996 17:55:50 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id RAA21044 for ; Tue, 15 Oct 1996 17:55:47 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa19747; 15 Oct 96 13:35:47 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa19743; 15 Oct 96 13:20:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06209; 15 Oct 96 13:20:18 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa28827; 15 Oct 96 2:19:29 EDT Received: from helmholtz.salk.edu by CS.CMU.EDU id aa06627; 15 Oct 96 2:18:22 EDT Received: (from zador@localhost) by helmholtz.salk.edu (8.7.5/8.7.3) id XAA29858; Mon, 14 Oct 1996 23:18:19 -0700 (PDT) Date: Mon, 14 Oct 1996 23:18:19 -0700 (PDT) From: Tony Zador Message-Id: <199610150618.XAA29858@helmholtz.salk.edu> To: connectionists@cs.cmu.edu Subject: Re: The Electrotonic Workbench Neuron is an excellent tool for computing the morphoelectrotonic transform (MET). However, for those who would prefer to use Mathematica, a toolkit is available at http://mrb.niddk.nih.gov/hagai/publ/Zador95/Abstract.html Several digitized cortical pyramidal neurons are also available at this site. The full published description of the MET can be found in: Zador AM; Agmon-Snir H; Segev I. The morphoelectrotonic transform: a graphical approach to dendritic function.Journal of Neuroscience, 1995 Mar, 15(3 Pt 1):1669-82. The Mathematica MET Toolkit was used to generate all the figures in this paper. ______________________________ Tony Zador Salk Institute MNL/S http://www.sloan.salk.edu/~zador ______________________________ From phkywong@uxmail.ust.hk Tue Oct 15 17:55:59 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id RAA28342 for ; Tue, 15 Oct 1996 17:55:52 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id RAA21048 for ; Tue, 15 Oct 1996 17:55:49 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab19747; 15 Oct 96 13:37:25 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id ab19743; 15 Oct 96 13:20:56 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa06214; 15 Oct 96 13:20:37 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa01917; 15 Oct 96 7:14:42 EDT Received: from uxmail.ust.hk by RI.CMU.EDU id aa02621; 15 Oct 96 7:14:06 EDT Received: from phsu2.ust.hk by uxmail.ust.hk id <102345-24300>; Tue, 15 Oct 1996 19:12:39 +0800 From: "Dr. Michael Wong" To: connectionists@cs.cmu.edu Subject: Paper available Message-Id: <96Oct15.191239+0800_hkt.102345-24300+615@uxmail.ust.hk> Date: Tue, 15 Oct 1996 19:12:36 +0800 The following paper, to be orally presented at NIPS'96, is now available via anonymous FTP. (7 pages) ============================================================================ FTP-host: physics.ust.hk FTP-files: pub/kymwong/rough.ps.gz Microscopic Equations in Rough Energy Landscape for Neural Networks K. Y. Michael Wong Department of Physics, The Hong Kong University of Science and Technology, Clear Water Bay, Kowloon, Hong Kong. E-mail address: phkywong@usthk.ust.hk ABSTRACT We consider the microscopic equations for learning problems in neural networks. The aligning fields of an example are obtained from the cavity fields, which are the fields if that example were absent in the learning process. In a rough energy landscape, we assume that the density of the metastable states obey an exponential distribution, yielding macroscopic properties agreeing with the first step replica symmetry breaking solution. Iterating the microscopic equations provide a learning algorithm, which results in a higher stability than conventional algorithms. ============================================================================ FTP instructions: unix> ftp physics.ust.hk Name: anonymous Password: your full email address ftp> cd pub/kymwong ftp> get rough.ps.gz ftp> quit unix> gunzip rough.ps.gz unix> lpr rough.ps (or ghostview rough.ps) From gordon@aic.nrl.navy.mil Thu Oct 17 09:16:25 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA01683 for ; Thu, 17 Oct 1996 09:16:19 -0500 Received: from cs.uwa.oz.au (bilby.cs.uwa.oz.au [130.95.1.11]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id JAA19065 for ; Thu, 17 Oct 1996 09:16:16 -0500 Received: from (parma.cs.uwa.oz.au [130.95.1.7]) by cs.uwa.oz.au (8.6.8/8.5) with SMTP id SAA23566; Thu, 17 Oct 1996 18:14:46 +0800 Message-Id: <199610171014.SAA23566@cs.uwa.oz.au> From: gordon@aic.nrl.navy.mil To: reinforce@cs.uwa.edu.au Cc: gordon@aic.nrl.navy.mil Subject: Call for Workshop Proposals Date: Wed, 16 Oct 96 11:29:25 EDT CALL FOR WORKSHOP PROPOSALS Fourteenth International Conference on Machine Learning July 12, 1997 Full and half day workshops will be held on Saturday, July 12, 1997 following the technical program of the Fourteenth International Conference on Machine Learning (ICML-97). Workshop proposals are invited in all areas of machine learning. Workshop attendees will be required to register for the main ICML-97 conference. There will be an additional fee for workshop attendance. Proposals for workshops should be a maximum of three (3) pages in length, and should contain: o A workshop title. o A technical description of the workshop and its objectives. o An explanation of why the workshop is currently of interest to the machine learning community. o A description of the workshop format, including invited speakers, panels, and discussion sessions. Please include the length of time planned for the workshop and a proposed schedule. o A description of the review and paper selection process that will be followed. o The names, postal and email addresses, and phone numbers of the workshop organizers, plus identification of the chair and/or key workshop contact. o A proposed limit, if any, on workshop attendance. o A list of researchers and/or research groups that work in the area and might be interested in attending the proposed workshop (this list need not be included in the 3 page limit). Please send workshop proposals and related inquiries, preferably by electronic mail in plain ASCII text, to: Diana Gordon Workshop Chair EMAIL: gordon@aic.nrl.navy.mil Naval Research Laboratory, Code 5514 4555 Overlook Avenue, S.W. Washington, D.C. 20375-5337 USA Proposals should be sent as soon as possible, but must be received by December 4, 1996. Notification of acceptance or rejection will be mailed to the organizer by January 6, 1997. Descriptions of accepted workshops will be made available via the World-Wide Web (see address below). Organizers of accepted workshops will be responsible for preparing and distributing a Call for Papers and Participation for their workshops. The ICML-97 Workshops Chair requires a copy of each accepted Workshop CFP by January 20, 1997 for display on the ICML-97 WWW site. The selection of papers, participants, and other workshop organizational matters such as the assembly of camera-ready copy of the Workshop proceedings are the responsibility of the Workshop organizers. ICML-97 will be responsible for local arrangements (i.e., rooms, equipment), collection of workshop registration fees, and printing and delivery of the workshop proceedings. ICML-97 will reimburse Workshop organizers for reasonable and limited costs (e.g., postage for submitting camera-ready proceedings, copying). TIMETABLE SUMMARY Submission of workshop proposals: December 4, 1996 Notification of acceptance or rejection: January 6, 1997 Accepted workshop CFPs due: January 20, 1997 Camera-ready proceedings due: May 28, 1997 (tentative) Workshops: July 12, 1997 -------------------------------------------------------------- More detailed information on the workshops and ICML-97 may be found at the ICML-97 Web site: http://cswww.vuse.vanderbilt.edu/~mlccolt/icml97/index.html -------------------------------------------------------------- From tgd@chert.CS.ORST.EDU Thu Oct 17 14:14:37 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id OAA06740 for ; Thu, 17 Oct 1996 14:14:31 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id OAA24830 for ; Thu, 17 Oct 1996 14:14:23 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa21923; 17 Oct 96 11:15:30 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa21921; 17 Oct 96 10:46:29 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa08795; 17 Oct 96 10:45:52 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa12112; 17 Oct 96 1:16:40 EDT Received: from chert.CS.ORST.EDU by EDRC.CMU.EDU id aa25453; 17 Oct 96 1:16:30 EDT Received: from edison.CS.ORST.EDU (edison.CS.ORST.EDU [128.193.38.69]) by chert.CS.ORST.EDU (8.7.1/8.6.10) with SMTP id WAA26250; Wed, 16 Oct 1996 22:14:10 -0700 (PDT) From: Tom Dietterich Received: by edison.CS.ORST.EDU (4.1/CS-Client) id AA03346; Wed, 16 Oct 96 22:16:19 PDT Date: Wed, 16 Oct 96 22:16:19 PDT Message-Id: <9610170516.AA03346@edison.CS.ORST.EDU> To: connectionists@cs.cmu.edu Subject: Paper available: Statistical Tests for Comparing Supervised Classification Learning Algorithms Reply-To: tgd@chert.CS.ORST.EDU Ftp-Host: ftp.cs.orst.edu Ftp-Filename: /pub/tgd/papers/stats.ps.gz The following paper is available from **Hardcopies are not available** Statistical Tests for Comparing Supervised Classification Learning Algorithms Thomas G. Dietterich Department of Computer Science Oregon State University Corvallis, OR 97331 Abstract: This paper reviews five statistical tests for determining whether one learning algorithm out-performs another on a particular learning task. These tests are compared experimentally to determine their probability of incorrectly detecting a difference when no difference exists (Type I error). Two widely-used statistical tests are shown to have high probability of Type I error in certain situations and should never be used. These tests are (a) a test for the difference of two proportions and (b) a paired-differences $t$ test based on taking several random train/test splits. A third test, a paired-differences $t$ test based on 10-fold cross-validation, exhibits somewhat elevated probability of Type I error. A fourth test, McNemar's test, is shown to have low Type I error. The fifth test is a new test, 5x2cv, based on 5 iterations of 2-fold cross-validation. Experiments show that this test also has good Type I error. The paper also measures the power (ability to detect algorithm differences when they do exist) of these tests. The 5x2cv test is shown to be slightly more powerful than McNemar's test. The choice of the best test is determined by the computational cost of running the learning algorithm. For algorithms that can be executed only once, McNemar's test is the only test with acceptable Type I error. For algorithms that can be executed ten times, the 5x2cv test is recommended, because it is slightly more powerful and because it directly measures variation due to the choice of training set. -- Thomas G. Dietterich Voice: 541-737-5559 Department of Computer Science FAX: 541-737-3014 Dearborn Hall, 303 URL: http://www.cs.orst.edu/~tgd Oregon State University Corvallis, OR 97331-3102 From l.s.smith@cs.stir.ac.uk Thu Oct 17 21:38:03 1996 Received: from lucy.cs.wisc.edu (lucy.cs.wisc.edu [128.105.2.11]) by sea.cs.wisc.edu (8.6.12/8.6.12) with ESMTP id VAA12007 for ; Thu, 17 Oct 1996 21:37:57 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU (TELNET-1.SRV.CS.CMU.EDU [128.2.254.108]) by lucy.cs.wisc.edu (8.6.12/8.6.12) with SMTP id VAA02175 for ; Thu, 17 Oct 1996 21:37:55 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa22468; 17 Oct 96 20:30:17 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa22466; 17 Oct 96 20:20:02 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa09185; 17 Oct 96 20:19:54 EDT Date: Thu, 17 Oct 1996 13:18:36 +0100 (BST) From: "Dr L S Smith (Staff)" Message-Id: <19961017T121836Z.NAA01062@katrine.cs.stir.ac.uk> Received: by NeXT.Mailer (1.100) Received: by NeXT Mailer (1.100) To: Connectionists@cs.cmu.edu Subject: CFP: 1st European Workshop on Neuromorphic Systems Cc: lss@cs.stir.ac.uk EWNS: 1st European Workshop on Neuromorphic Systems 29-31 August 1997, University of Stirling, Stirling, Scotland First Call for Papers Organisers: Centre for Cognitive and Computational Neuroscience University of Stirling, Scotland and Department of Electrical Engineering University of Edinburgh, Scotland First Call for Papers Neuromorphic systems are implementations in silicon of sensory and neural systems whose architecture and design are based on neurobiology. This growing area proffers exciting possibilities such as sensory systems which can compete with human senses and pattern recognition systems that can run in real-time. The area is at the intersection of many disciplines: neurophysiology, computer science and electrical engineering. Papers are requested in the following areas: Design issues in sensorineural neuromorphic systems: auditory, visual, olfactory, proprioception, sensorimotor systems. Designs for silicon implementations of neural systems. Papers not exceeding 8 A4 pages are requested: these should be sent to Dr. Leslie Smith Department of Computing Science University of Stirling Stirling FK9 4LA Scotland email: lss@cs.stir.ac.uk FAX (44) 1786 464551 We also propose to hold a number of discussion sessions on some of the questions above. Short position papers (less than 4 pages) are requested. Key Dates Submission Deadline: Mon 7th April 1997 Notification of Acceptance: June 2nd 1997 Further information is on the WWW at http://www.cs.stir.ac.uk/~lss/Neuromorphic/Info1.html