From andre@icmsc.sc.usp.br Mon Aug 19 20:49:45 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 UAA01930 for ; Mon, 19 Aug 1996 20:49:41 -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 UAA28636 for ; Mon, 19 Aug 1996 20:49:39 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa02727; 19 Aug 96 20:52:44 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa02725; 19 Aug 96 20:32:18 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa14853; 19 Aug 96 20:31:38 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa10389; 19 Aug 96 19:27:32 EDT Received: from vmcisc.cisc.sc.usp.br by CS.CMU.EDU id aa27929; 19 Aug 96 19:26:58 EDT Received: from suncisc.cisc.sc.usp.br by vmcisc.cisc.sc.usp.br (IBM VM SMTP V2R2) with TCP; Mon, 19 Aug 96 20:21:48 EST Received: from taba (taba.icmsc.sc.usp.br) by suncisc.cisc.sc.usp.br (4.1/SMI-4.1) id AA03254; Mon, 19 Aug 96 20:25:13 EST Received: from icmsc.sc.usp.br by taba (SMI-8.6/SMI-SVR4) id UAA06533; Mon, 19 Aug 1996 20:23:02 -0300 Date: Mon, 19 Aug 1996 20:23:02 -0300 From: " Andre Carlos P. de Leon F. de Carvalho " Message-Id: <199608192323.UAA06533@taba> To: connectionists@cs.cmu.edu Subject: SBRN 96 - LAST CALL 3rd Brazilian Symposium on Neural Networks Recife, November 12 - 14, 1996 Sponsored by the Brazilian Computer Society (SBC) Second Call for Papers The Third Brazilian Symposium on Neural Networks will be held at the Federal University of Pernambuco, in Recife (Brazil), from the 12nd to the 14th of November, 1996. The SBRN symposia, as they were initially named, are organized by the interest group in Neural Networks of the Brazilian Computer Society since 1994. The third version of the meeting follows a very successfull organization of the previous events which brought together the main developments of the area in Brazil and had the participation of many national and international researchers both as invited speakers and as authors of papers presented at the symposium. Recife is a very pleasant city in the northeast of Brazil, known by its good climate and beautiful beaches, with sunshine throughout almost the whole year. The city, whose name originated from the coral formations in the seaside port and beaches, is in a strategic touristic situation in the region and offers a good variety of hotels both in the city historic center and at the seaside resort. Scientific papers will be analyzed by the program committee. This analysis will take into account originality, significance to the area, and clarity. Accepted papers will be fully published in the conference proceedings. MAJOR TOPICS: The major topics of interest include, but are not limited to: * Biological Perspectives * Theoretical Models * Algorithms and Architectures * Learning Models * Hardware Implementation * Signal Processing * Robotics and Control * Parallel and Distributed Implementations * Pattern Recognition * Image Processing * Optimization * Cognitive Science * Hybrid Systems * Dynamic Systems * Genetic Algorithms * Fuzzy Logic * Applications INTERNATIONAL INVITED SPEAKERS: * "Adaptive Wavelets for Pattern Recognition" by Professor Harold Szu , Director of the Center for Advanced Computer Studies, University of Southwestern Louisiana * "Recurrent Neural Networks: El Dorado or Fort Knox?" by Professor C. Lee Giles , NEC Research Institute and University of Maryland, College Park * "Case-based Reasoning and Neural Networks - a Fruitful Breed?" by Professor Agnar Aamodt , Department of Informatics, University of Trondheim - Norway PROGRAM COMMITTEE: * Teresa Bernarda Ludermir - DI/UFPE * Andri C. P. L. F. de Carvalho - ICMSC/USP (Chair) * Germano C. Vasconcelos - DI/UFPE * Anttnio de Padua Braga - DELT/UFMG * Dmbio Leandro Borges - CEFET/PR * Paulo Martins Engel - II/UFRGS * Ricardo Machado - PUC/Rio * Valmir Barbosa - COPPE/UFRJ * Weber Martins - EEE/UFG ORGANISING COMMITTEE: * Teresa Bernarda Ludermir - DI/UFPE (Chair) * Edson Costa de Barros Carvalho Filho - DI/UFPE * Germano C. Vasconcelos - DI/UFPE * Paulo Jorge Leitco Adeodato - DI/UFPE SUBMISSION PROCEDURE: The symposium seeks contributions to the state of the art and future perspectives of Neural Networks research. Submitted papers must be in Portuguese, English or Spanish. The submissions must include the original and three copies of the paper and must follow the format below (Electronic mail and FAX submissions are NOT accepted). The paper must be printed using a laser printer, in two-column format, not numbered, 8.5 X 11.0 inch (21,7 X 28.0 cm). It must not exceed eight pages, including all figures and diagrams. The font size should be 10 pts, such as Times-Roman or equivalent, with the following margins: right and left 2.5 cm, top 3.5 cm, and bottom 2.0 cm. The first page should contain the paper's title, the complete author(s) name(s), affiliation(s), and mailing address(es), followed by a short (150 words) abstract and a list of descriptive key words. The submission should also include an accompanying letter containing the following information : * Manuscript title * First author's name, mailing address and e-mail * Technical area of the paper Authors may use the Latex files sbrn.tex and sbrn.sty for preparing their manuscripts. The postscript file sbrn.ps is also available. Alternately, all those files, together with an equivalent file in WORD, can be retrieved by anonymous ftp following the instructions given below : ftp ftp.di.ufpe.br (LOGIN :) anonymous (PASSWORD :) (your email address) cd pub/events/IIISBRN bin get sbrn.tex (or sbrn.doc) get sbrn.sty bye SUBMISSION ADDRESS: Four copies (one original and three copies) must be submitted to: Prof. Andri Carlos Ponce de Leon Ferreira de Carvalho Coordenador do Comitj de Programa - III SBRN Departamento de Cijncias de Computagco e Estatmstica ICMSC - Universidade de Sco Paulo Caixa Postal 668 CEP 13560.070 Sco Carlos, SP Phone: +55 162 726222 FAX: +55 162 749150 E-mail: IIISBRN@di.ufpe.br IMPORTANT DATES: August 30, 1996 (mailing date): Deadline for paper submission September 30, 1996 : Notification of acceptance/rejection November, 12-14 1996 : III SBRN ADDITIONAL INFORMATION: * Up-to-minute information about the symposium is available on the World Wide Web (WWW) at http://www.di.ufpe.br/~IIISBRN/web_sbrn * Questions can be sent by E-mail to IIISBRN@di.ufpe.br Profa. Teresa Bernarda Ludermir Coordenadora Geral do III SBRN Laboratory of Intelligent Computing (LCI) Departamento de Informatica Universidade Federal de Pernambuco Caixa Postal 7851 CEP 50.732-970 Recife-PE Fone : +55 81 271-8430 FAX: +55 81 271-8438 E-mail: IIISBRN@di.ufpe.br We look forward to seeing you in Recife ! From robert@fit.qut.edu.au Wed Aug 21 06:35:43 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 GAA25501 for ; Wed, 21 Aug 1996 06:35:38 -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 GAA11097 for ; Wed, 21 Aug 1996 06:35:36 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa05039; 21 Aug 96 6:27:48 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa05037; 21 Aug 96 6:09:52 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa16214; 21 Aug 96 6:09:36 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa01902; 21 Aug 96 1:52:39 EDT Received: from ocean.fit.qut.edu.au by EDRC.CMU.EDU id aa12194; 21 Aug 96 1:51:53 EDT Received: (from robert@localhost) by ocean.fit.qut.edu.au (8.7.4/8.7.2) id PAA14160; Wed, 21 Aug 1996 15:42:19 +1000 (EST) Date: Wed, 21 Aug 1996 15:42:18 +1000 (EST) From: Robert Andrews To: connectionists@cs.cmu.edu Subject: NIPS*96 Rule Extraction W'shop Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII ============================================================= FIRST CALL FOR PAPERS NIPS*96 POST-CONFERENCE WORKSHOP -------------------------------------------- RULE-EXTRACTION FROM TRAINED NEURAL NETWORKS -------------------------------------------- Snowmass (Aspen), Colorado, USA Fri December 6th, 1996 Robert Andrews & Joachim Diederich Neurocomputing Research Centre Queensland University of Technology Brisbane 4001 Queensland, Australia Fax: +61 7 864-1801 E-mail: robert@fit.qut.edu.au E-mail: joachim@fit.qut.edu.au Rule extraction can be defined as the process of deriving a symbolic description of a trained Artificial Neural Network (ANN). Ideally the rule extraction process results in a symbolic description which closely mimics the behaviour of the network in a concise and comprehensible form. The merits of including rule extraction techniques as an adjunct to conventional Artificial Neural Network techniques include: a) the provision of a 'User Explanation' capability; b) improvement of the generalisation capabilities of ANN solutions by allowing identification of regions of input space not adequately represented; c) data exploration and the induction of scientific theories by the discovery and explicitation of previously unknown dependencies and relationships in data sets; d) knowledge acquistion for symbolic AI systems by overcoming the knowledge engineering bottleneck; e) the potential to contribute to the understanding of how symbolic and connectionist approaches to AI can be profitably integrated. An ancillary problem to that of rule extraction from trained ANNs is that of using the ANN for the `refinement' of existing rules within symbolic knowledge bases. The goal in rule refinement is to use a combination of ANN learning and rule extraction techniques to produce a `better' (ie a `refined') set of symbolic rules which can then be applied back in the original problem domain. In the rule refinement process, the initial rule base (ie what may be termed `prior knowledge') is inserted into an ANN by programming some of the weights. The rule refinement process then proceeds in the same way as normal rule extraction viz (1) train the network on the available data set(s); and (2) extract (in this case the `refined') rules - with the proviso that the rule refinement process may involve a number of iterations of the training phase rather than a single pass. The objective of this workshop is to provide a discussion platform for researchers and practitioners interested in all aspects of rule extraction from trained artificial neural networks. The workshop will examine current techniques for providing an explanation component for ANNs including rule extraction, extraction of fuzzy rules, rule initialisation and rule refinement. Other topics for discussion include computational complexity of rule extraction algorithms, criteria for assessing rule quality, and issues relating to generalisation differences between the ANN and the extracted rule set. The workshop will also discuss ways in which ANNs and rule extraction techniques may be profitably employed in commercial, industrial, and scientific application areas. The one day workshop will be a mixture of position papers and panel discussions. Papers presented in the mini-conference sessions will be of 20 minutes duration with ample time for questions/discussions afterwards. DISCUSSION POINTS FOR WORKSHOP PARTICIPANTS 1. Decompositional vs. learning approaches to rule-extraction from ANNs - What are the advantages and disadvantages w.r.t. performance, solution time, computational complexity, problem domain etc. Are decompositional approaches always dependent on a certain ANN architecture? 2. Rule-extraction from trained neural networks v symbolic induction. What are the relative strength and weaknesses? 3. What are the most important criteria for rule quality? 4. What are the most suitable representation languages for extracted rules? How does the extraction problem vary across different languages? 5. What is the relationship between rule-initialisation (insertion) and rule-extraction? For instance, are these equivalent or complementary processes? How important is rule-refinement by neural networks? 6. Rule-extraction from trained neural networks and computational learning theory.Is generating a minimal rule-set which mimics an ANN a hard problem? 7. Does rule-initialisation result in improved generalisation and faster learning? 8. To what extent are existing extraction algorithms limited in their applicability? How can these limitations be addressed? 9. Are there any interesting rule-extraction success stories? That is, problem domains in which the application of rule-extraction methods has resulted in an interesting or significant advance. SUBMISSION OF WORKSHOP EXTENDED ABSTRACTS/PAPERS Authors are invited to submit 3 copies of either an extended abstract or full paper relating to one of the topic areas listed above. Papers should be written in English in single column format and should be limited to no more than eight, (8) sides of A4 paper including figures and references. NIPS style files are available at http://www.cs.cmu.edu/afs/cs/project/cnbc/nips/formatting/nips.sty http://www.cs.cmu.edu/afs/cs/project/cnbc/nips/formatting/nips.tex http://www.cs.cmu.edu/afs/cs/project/cnbc/nips/formatting/nips.ps Please include the following information in an accompanying cover letter: Full title of paper, presenting author's name, address, and telephone and fax numbers, authors e-mail address. Submission Deadline is October 7th,1996 with notification to authors by 31st October,1996. For further information, inquiries, and paper submissions please contact: Robert Andrews Queensland University of Technology GPO Box 2434 Brisbane Q. 4001. Australia. phone +61 7 864-1656 fax +61 7 864-1969 email robert@fit.qut.edu.au More information about the NIPS*96 workshop series is available from: WWW: http://www.fit.qut.edu.au/~robert/nips96.html From sml@esesparc2.essex.ac.uk Thu Aug 22 14:14:12 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 OAA10941 for ; Thu, 22 Aug 1996 14:14:03 -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 OAA04902 for ; Thu, 22 Aug 1996 14:14:01 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa07261; 22 Aug 96 14:07:54 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa07258; 22 Aug 96 13:38:01 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa17419; 22 Aug 96 13:37:44 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa22925; 22 Aug 96 9:02:07 EDT Received: from [155.245.10.186] by CS.CMU.EDU id aa05164; 22 Aug 96 9:01:43 EDT Received: from esesparc2.essex.ac.uk by seralph6.essex.ac.uk; (5.65v3.2/1.1.8.2/14Feb95-1154AM) id AA29284; Thu, 22 Aug 1996 14:01:26 +0100 Date: Thu, 22 Aug 1996 14:01:17 +0100 (BST) From: Lucas S M To: Connectionists%CS.CMU.EDU@seralph6.essex.ac.uk Subject: structuring chromosomes for total neural network evolution Message-Id: Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII subject: structuring chromosomes for total neural network evolution The following two papers discuss recent work on a simple unified approach to evolving ALL aspects of a neural network, including its learning algorithm (if any). The first uses a grammar based chromosome, the second uses a set-based chromosome. The latter approach appears particularly promising as a method of part designing/ part evolving neural networks. ----------------------------------------------------------------------- Title: Growing Adaptive Neural Networks with Graph Grammars Author: S.M. Lucas Date: April 1995 In: Proceedings of European Symposium on Artificial Neural Networks (ESANN '95) (pp. 235 -- 240) Abstract ---------- This paper describes how graph grammars with attributes may be used to grow neural networks. The grammar facilitates a very compact and declarative description of every aspect of a neural architecture; this is important from a software/neural engineering point of view, since the descriptions are much easier to write and maintain than programs written in a high-level language, such as C++, and do not require programming ability. The output of the growth process is a neural network that can be transformed into a Postscript representation for display purposes, or simulated using a separate neural network simulation program, or mapped directly into hardware in some cases. In this approach, there is no separate learning algorithm; learning proceeds (if at all) as an intrinsic part of the network behaviour. This has interesting application in the evolution of neural nets, since now it is possible to evolve all aspects of a network (including the learning `algorithm') within a single unified paradigm. As an example, a grammar is given for growing a multi-layer perceptron with active weights that has the error back-propagation learning algorithm embedded in its structure. This paper is available through my web page: http://esewww.essex.ac.uk/~sml or via anonymous ftp: ftp tarifa.essex.ac.uk cd /images/sml/reports get esann95.ps ----------------------------------------------------------------------- Title: Evolving Neural Network Learning Behaviours with Set-Based Chromosomes Author: S.M. Lucas Date: April 1996 In: Proceedings of European Symposium on Artificial Neural Networks (ESANN '96) (pp. 291 -- 296) Abstract ---------- This paper describes a set-based chromosome for describing neural networks. The chromosome etween sets. Each set is updated in order, as are the neurons in that set, in accordance with a simple pre-specified algorithm. This allows all details of a neural architecture, including its learning behaviour to be specified in a simple and purely declarative manner. To evolve a learning behaviour for a particular network architecture, certain details of the architecture are pre-specified by defining a chromosome template, with some of the genes fixed, and others allowed to vary. In this paper, a learning perceptron is evolved, by fixing the feedforward and error-computation parts of the chromosome, then evolving the feedback part responsible for computing weight updates. Using this methodology, learning behaviours with similar performance to the delta rule have been evolved. This paper is available through my web page: http://esewww.essex.ac.uk/~sml or via anonymous ftp: ftp tarifa.essex.ac.uk cd /images/sml/reports get esann96.ps ----------------------------------------------------------------------- Comments and criticisms welcome. Simon Lucas ------------------------------------------------ Dr. Simon Lucas Department of Electronic Systems Engineering University of Essex Colchester CO4 3SQ United Kingdom http://esewww.essex.ac.uk/~sml Tel: (+44) 1206 872935 Fax: (+44) 1206 872900 Email: sml@essex.ac.uk secretary: Mrs Wendy Ryder (+44) 1206 872437 ------------------------------------------------- From bruce@bme1.image.uky.edu Thu Aug 22 19:22:58 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 TAA20486 for ; Thu, 22 Aug 1996 19:22:51 -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 TAA09742 for ; Thu, 22 Aug 1996 19:22:50 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa07423; 22 Aug 96 15:14:29 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa07421; 22 Aug 96 15:02:38 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa17555; 22 Aug 96 15:02:29 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa28371; 22 Aug 96 14:45:54 EDT Received: from ukcc.uky.edu by EDRC.CMU.EDU id aa20521; 22 Aug 96 14:44:41 EDT Received: from image.uky.edu by UKCC.uky.edu (IBM VM SMTP V2R3) with TCP; Thu, 22 Aug 96 14:42:30 EDT Received: from @bme1.image.uky.edu ([128.163.176.203]) by image.uky.edu (4.1/SMI-4.1) id AA01571; Thu, 22 Aug 96 14:45:12 EDT Date: Thu, 22 Aug 96 14:45:12 EDT Message-Id: <9608221845.AA01571@image.uky.edu> X-Sender: bruce@bme1.image.uky.edu X-Mailer: Windows Eudora Version 1.4.4 Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" To: connectionists@cs.cmu.edu From: Eugene Bruce POSTDOCTORAL POSITION(SENSORIMOTOR INTEGRATION AND DYNAMICAL SYSTEMS) Respiratory Dynamics Lab, University of Kentucky Center for Biomedical Engineering This position is part of an NIH-funded project to identify causes of irregular breathing and apnea. The project involves experimental and computational studies aimed at understanding nonlinear modulation of respiratory rhythm by sensory afferents from the lungs and upper airway. Specific sub-projects include: (1) characterization of vagal deflation receptors in rats from single-unit recordings; (2) analysis of modulation of breathing pattern by upper airway afferents using techniques from nonlinear dynamics, including the development of new theoretical approaches to signal processing; (3) mathematical modelling of the integration of sensory afferents with neural circuits for respiratory pattern formation; (4) experimental analysis and modelling of responses of upper airway and chest wall muscles to transient respiratory stimuli using linear and nonlinear system identification methods. Future work will address the development of an in-vitro brainstem-spinal cord preparation for studying respiratory sensorimotor integration. The ideal applicant will be able to contribute to aspects of both the experimental studies and the modelling or signal analysis efforts. The position is available immediately. More information about the laboratory can be found at the URL http://www.uky.edy/RGS/CBME/bruce.html. Information about related neuroscience activities at the Center is available at http://www.uky.edu/RGS/CBME/CBMENeuralControl.html. Additional information about this position is available via email inquiries to bruce@bme1.image.uky.edu, or by telephone (606-257-3774). Applications (curriculum vitae and names of references) may be sent to Dr. Eugene Bruce by email, or by postal mail to Wenner Gren Research Laboratory, University of Kentucky, Rose Street, Lexington, KY 40506-0070. (Posted on 8/22/96.) Eugene Bruce, Ph. D. Center for Biomedical Engineering Univ. of Kentucky BRUCE@BME1.IMAGE.UKY.EDU From dhw@almaden.ibm.com Fri Aug 23 02:49:48 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 CAA29354 for ; Fri, 23 Aug 1996 02:49:42 -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 CAA14155 for ; Fri, 23 Aug 1996 02:49:40 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa08350; 22 Aug 96 23:10:19 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa08345; 22 Aug 96 23:02:04 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa17821; 22 Aug 96 23:01:20 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa03292; 22 Aug 96 18:34:39 EDT Received: from ALMADEN.IBM.COM by RI.CMU.EDU id aa08328; 22 Aug 96 18:33:54 EDT Received: from ALMADEN by almaden.ibm.com (IBM VM SMTP V2R2) with BSMTP id 0189; Thu, 22 Aug 96 15:32:42 PDT Received: by ALMADEN (XAGENTA 4.0) id 8330; Thu, 22 Aug 1996 15:32:41 -0700 Received: by buson.almaden.ibm.com (AIX 4.1/UCB 5.64/4.03) id AA24700; Thu, 22 Aug 1996 15:33:47 -0700 Date: Thu, 22 Aug 1996 15:33:47 -0700 From: dhw@almaden.ibm.com MMDF-Warning: Parse error in original version of preceding line at DST.BOLTZ.CS.CMU.EDU Message-Id: <9608222233.AA24700@buson.almaden.ibm.com> To: Connectionists@cs.cmu.edu Subject: Paper announcements *** Paper Announcements *** ==================================================================== The following new paper is now available with anonymous ftp to ftp.santafe.edu, in the directory pub/dhw_ftp, under the names BS.ps.Z and BS.ps.Z.encoded. Any comments are welcomed. * COMBINING STACKING WITH BAGGING TO IMPROVE A LEARNING ALGORITHM by David H. Wolpert and William G. Macready Abstract: In bagging \cite{breiman:bagging} one uses bootstrap replicates of the training set \cite{efron:computers, efron.tibshirani:introduction} to improve a learning algorithm's performance, often by tens of percent. This paper presents several ways that stacking \cite{wolpert:stacked,breiman:stacked} can be used in concert with the bootstrap procedure to achieve a further improvement on the performance of bagging for some regression problems. In particular, in some of the work presented here, one first converts a single underlying learning algorithm into several learning algorithms. This is done by bootstrap resampling the training set, exactly as in bagging. The resultant algorithms are then combined via stacking. This procedure can be viewed as a variant of bagging, where stacking rather than uniform averaging is used to achieve the combining. The stacking improves performance over simple bagging by up to a factor of 2 on the tested problems, and never resulted in worse performance than simple bagging. In other work presented here, there is no step of converting the underlying learning algorithm into multiple algorithms, so it is the improve-a-single-algorithm variant of stacking that is relevant. The precise version of this scheme tested can be viewed as using the bootstrap and stacking to estimate the input-dependence of the statistical bias and then correct for it. The results are preliminary, but again indicate that combining stacking with the bootstrap can be helpful. ==================================================================== The following paper has been previously announced. A new version, incorporating major modifications of the original, is now available at ftp.santafe.edu, in pub/dhw_ftp, as estimating.baggings.error.ps.Z or estimating.baggings.error.ps.Z.encoded. The new version shows in particular how the generalization error of a bagged version of a learning algorithm can be estimated with more accuracy than that afforded by using cross-validation on the original algorithm. Any comments are welcomed. * AN EFFICIENT METHOD TO ESTIMATE BAGGING'S GENERALIZATION ERROR by David H. Wolpert and William G. Macready Abstract: In bagging \cite{Breiman:Bagging} one uses bootstrap replicates of the training set \cite{Efron:Stat,BootstrapIntro} to try to improve a learning algorithm's performance. The computational requirements for estimating the resultant generalization error on a test set by means of cross-validation are often prohibitive; for leave-one-out cross-validation one needs to train the underlying algorithm on the order of $m\nu$ times, where $m$ is the size of the training set and $\nu$ is the number of replicates. This paper presents several techniques for exploiting the bias-variance decomposition \cite{Geman:Bias, Wolpert:Bias} to estimate the generalization error of a bagged learning algorithm without invoking yet more training of the underlying learning algorithm. The best of our estimators exploits stacking \cite{Wolpert:Stack}. In a set of experiments reported here, it was found to be more accurate than both the alternative cross-validation-based estimator of the bagged algorithm's error and the cross-validation-based estimator of the underlying algorithm's error. This improvement was particularly pronounced for small test sets. This suggests a novel justification for using bagging--- improved estimation of generalization error. ==================================================================== The following paper has been previously announced. A new version, incorporating major modifications of the original, is now available at ftp.santafe.edu, in pub/dhw_ftp, as bias.plus.ps.Z or bias.plus.ps.Z.encoded. The new version contains in particular an analysis of the Friedman effect, discussed in Jerry Friedman's recently announced paper on 0-1 loss. Any comments are welcomed. * ON BIAS PLUS VARIANCE by David H. Wolpert Abstract: This paper presents several additive "corrections" to the conventional quadratic loss bias- plus-variance formula. One of these corrections is appropriate when both the target is not fixed (as in Bayesian analysis) and also training sets are averaged over (as in the conventional bias-plus- variance formula). Another additive correction casts conventional fixed-training-set Bayesian analysis directly in terms of bias-plus-variance. Another correction is appropriate for measuring full generalization error over a test set rather than (as with conventional bias-plus-variance) error at a single point. Yet another correction can help explain the recent counter-intuitive bias-variance decomposition of Friedman for zero-one loss. After presenting these corrections this paper then discusses some other loss-function-specific aspects of supervised learning. In particular, there is a discussion of the fact that if the loss function is a metric (e.g., zero-one loss), then there is bound on the change in generalization error accompanying changing the algorithm's guess from h1 to h2 that depends only on h1 and h2 and not on the target. This paper ends by presenting versions of the bias-plus-variance formula appropriate for logarithmic and quadratic scoring, and then all the ad ditive corrections appropriate to those formulas. All the correction terms presented in this paper are a covariance, between the learning algorithm and the posterior distribution over targets. Accordingly, in the (very common) contexts in which those terms apply, there is not a "bias-variance trade-off", or a "bias-variance dilemma", as one often hears. Rather there is a bias-variance-cova riance trade-off. From nin@cns.brown.edu Fri Aug 23 18:43:05 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 SAA22939 for ; Fri, 23 Aug 1996 18:42:57 -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 SAA26585 for ; Fri, 23 Aug 1996 18:42:55 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10156; 23 Aug 96 18:33:32 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10154; 23 Aug 96 18:12:14 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa18460; 23 Aug 96 18:11:57 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa16420; 23 Aug 96 12:19:05 EDT Received: from cns.brown.edu by RI.CMU.EDU id aa11708; 23 Aug 96 12:18:27 EDT Received: by cns.brown.edu (4.1/1.00) id AA07816; Fri, 23 Aug 96 12:07:32 EDT Date: Fri, 23 Aug 96 12:07:32 EDT From: Nathan Intrator Message-Id: <9608231607.AA07816@cns.brown.edu> To: Connectionists@cs.cmu.edu Subject: Paper announcements Cc: nin@cns.brown.edu *** Papers Announcements *** The following papers are now available from my research page: http://www.physics.brown.edu/people/nin/research.html Comments are welcomed. ----------------------------------------------------------------------- Classifying Seismic Signals by Integrating Ensembles of Neural Networks Yair Shimshoni and Nathan Intrator ftp://cns.brown.edu/nin/papers/hong-kong.ps.Z This paper proposes a classification scheme based on the integration of multiple Ensembles of ANNs. It is demonstrated on a classification problem, in which Seismic recordings of Natural Earthquakes must be distinguished from the recordings of Artificial Explosions. A Redundant Classification Environment consists of several Ensembles of Neural Networks is created and trained on Bootstrap Sample Sets, using various data representations and architectures. The ANNs within the Ensembles are aggregated (as in Bagging) while the Ensembles are integrated non-linearly, in a signal adaptive manner, using a posterior confidence measure based on the agreement (variance) within the Ensembles. The proposed Integrated Classification Machine achieved 92.1\% correct classification on the seismic test data. Cross Validation evaluations and comparisons indicate that such integration of a collection of ANN's Ensembles is a robust way for handling high dimensional problems with a complex non-stationary signal space as in the current Seismic Classification problem. To appear: Proceedings of ICONIP 96 ----------------------------------------------------------------------- Learning low dimensional representations of visual objects with extensive use of prior knowledge Nathan Intrator and Shimon Edelman ftp://cns.brown.edu/nin/papers/ml1.ps.Z Learning to recognize visual objects from examples requires the ability to find meaningful patterns in spaces of very high dimensionality. We present a method for dimensionality reduction which effectively biases the learning system by combining multiple constraints via an extensive use of class labels. The use of multiple class labels steers the resulting low-dimensional representation to become invariant to those directions of variation in the input space that are irrelevant to classification; this is done merely by making class labels independent of these directions. We also show that prior knowledge of the proper dimensionality of the target representation can be imposed by training a multiple-layer bottleneck network. A series of computational experiments involving parameterized fractal images and real human faces indicate that the low-dimensional representation extracted by our method leads to improved generalization in the learned tasks, and is likely to preserve the topology of the original space. To appear: EXPLANATION-BASED NEURAL NETWORK LEARNING: A LIFELONG LEARNING APPROACH. Editor: SEBASTIAN THRUN ----------------------------------------------------------------------- Bootstrapping with Noise: An Effective Regularization Technique Yuval Raviv and Nathan Intrator ftp://cns.brown.edu/nin/papers/spiral.ps.Z Bootstrap samples with noise are shown to be an effective smoothness and capacity control technique for training feed-forward networks and for other statistical methods such as generalized additive models. It is shown that noisy bootstrap performs best in conjunction with weight decay regularization and ensemble averaging. The two-spiral problem, a highly non-linear noise-free data, is used to demonstrate these findings. The combination of noisy bootstrap and ensemble averaging is also shown useful for generalized additive modeling, and is also demonstrated on the well known Cleveland Heart Data \cite{Detrano89}. To appear: Connection Science, Speciall issue on Combining Estimators. From jim@stats.gla.ac.uk Fri Aug 23 18:43:06 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 SAA22941 for ; Fri, 23 Aug 1996 18:42:58 -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 SAA26587 for ; Fri, 23 Aug 1996 18:42:56 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10177; 23 Aug 96 18:42:56 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10158; 23 Aug 96 18:13:51 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa18469; 23 Aug 96 18:13:21 EDT Received: from RI.CMU.EDU by B.GP.CS.CMU.EDU id aa16870; 23 Aug 96 12:48:55 EDT Received: from [130.209.236.41] by RI.CMU.EDU id aa11848; 23 Aug 96 12:48:24 EDT Message-Id: <17769.199608231649@pole.stats.gla.ac.uk> Date: Fri, 23 Aug 1996 17:49:16 +0100 From: Jim Kay Received: (from jim@localhost sender jim) by pole.stats.gla.ac.uk (8.6.10/UK-2.2a/stats) id RAA17769 for connectionists@cs.cmu.edu; Fri, 23 Aug 1996 17:49:16 +0100 To: connectionists@cs.cmu.edu Subject: TR on Contextually Guided Unsupervised Learning/Multivariate Processors Technical Report Available CONTEXTUALLY GUIDED UNSUPERVISED LEARNING USING LOCAL MULTIVARIATE BINARY PROCESSORS Jim Kay Department of Statistics University of Glasgow Dario Floreano MicroComputing Laboratory Swiss Federal Institute of Technology Bill Phillips Centre for Cognitive and Computational Neuroscience University of Stirling We consider the role of contextual guidance in learning and processing within multi-stream neural networks. Earlier work (Kay \& Phillips, 1994, 1996; Phillips et al., 1995) showed how the goals of feature discovery and associative learning could be fused within a single objective, and made precise using information theory, in such a way that local binary processors could extract a single feature that is coherent across streams. In this paper we consider multi-unit local processors, with multivariate binary outputs, that enable a greater number of coherent features to be extracted. Using the Ising model, we define a class of information-theoretic objective functions and also local approximations, and derive the learning rules in both cases. These rules have similarities to, and differences from, the celebrated BCM rule. Local and global versions of Infomax appear as by-products of the general approach, as well as multivariate versions of Coherent Infomax. Focussing on the more biologically plausible local rules, we describe some computational experiments designed to investigate specific properties of the processors and the general approach. The main conclusions are: 1. The local methodology introduced in the paper has the required functionality. 2. Different units within the multi-unit processors learned to respond to different aspects of their receptive fields. 3. The units within each processor generally produced a distributed code in which the outputs were correlated, and which was robust to damage; in the special case where the number of units available was only just sufficient to transmit the relevant information, a form of competitive learning was produced. 4. The contextual connections enabled the information correlated across streams to be extracted, and, by improving feature detection with weak or noisy inputs, they played a useful role in short-term processing and in improving generalization. 5. The methodology allows the statistical associations between distributed self-organizing population codes to be learned. This technical report is available in compressed Postscript by anonymous ftp from: ftp.stats.gla.ac.uk or from the following URL: ftp://ftp.stats.gla.ac.uk/pub/jim/NNkfp.ps.Z Some earlier reports and general references are available from the URL: http://www.stats.gla.ac.uk/~jim/nn.html ----------------------------------------------------------------------- Jim Kay jim@stats.gla.ac.uk From nkasabov@commerce.otago.ac.nz Sat Aug 24 05:02:54 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 FAA27671 for ; Sat, 24 Aug 1996 05:02:45 -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 FAA29988 for ; Sat, 24 Aug 1996 05:02:43 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10922; 24 Aug 96 0:21:08 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10919; 24 Aug 96 0:12:40 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa18619; 24 Aug 96 0:12:22 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa22967; 23 Aug 96 18:45:32 EDT Received: from legolas.otago.ac.nz by CS.CMU.EDU id aa20713; 23 Aug 96 18:45:06 EDT Received: from jupiter.otago.ac.nz (jupiter.otago.ac.nz [139.80.180.14]) by legolas.otago.ac.nz (8.7.1/8.7.1) with ESMTP id KAA15954 for ; Sat, 24 Aug 1996 10:52:24 +1200 Received: from JUPITER/SpoolDir by jupiter.otago.ac.nz (Mercury 1.20); 24 Aug 96 10:44:52 +1100 Received: from SpoolDir by JUPITER (Mercury 1.20); 24 Aug 96 10:44:37 +1100 From: Nikola Kasabov Organization: University of Otago To: Connectionists@cs.cmu.edu Date: Sat, 24 Aug 1996 10:44:32 -1200 Subject: ICONIP/ANZIIS/ANNES'97 CFP Priority: normal X-mailer: Pegasus Mail for Windows (v2.23) Message-ID: <23DE8694E89@jupiter.otago.ac.nz> ICONIP'97 jointly with ANZIIS'97 and ANNES'97 The Fourth International Conference on Neural Information Processing-- The Annual Conference of the Asian Pacific Neural Network Assembly, jointly with The Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems, and The Third New Zealand International Conference on Artificial Neural Networks and Expert Systems 24-28 November, 1997 Dunedin/Queenstown, New Zealand In 1997, the annual conference of the Asian Pacific Neural Network Assembly, ICONIP'97, will be held jointly with two other major international conferences in the Asian Pacific Region, the Fifth Australian and New Zealand International Conference on Intelligent Information Processing Systems (ANZIIS'97) and the Third New Zealand International Conference on Artificial Neural Networks and Expert Systems (ANNES'97), from 24 to 28 November 1997 in Dunedin and Queenstown, New Zealand. The joint conference will have three parallel streams: Stream1: Neural Information Processing Stream2: Computational Intelligence and Soft Computing Stream3: Intelligent Information Systems and their Applications TOPICS OF INTEREST Stream1: Neural Information Processing * Neurobiological systems * Cognition * Cognitive models of the brain * Dynamical modelling, chaotic processes in the brain * Brain computers, biological computers * Consciousness, awareness, attention * Adaptive biological systems * Modelling emotions * Perception, vision * Learning languages * Evolution Stream2: Computational Intelligence and Soft Computing * Artificial neural networks: models, architectures, algorithms * Fuzzy systems * Evolutionary programming and genetic algorithms * Artificial life * Distributed AI systems, agent-based systems * Soft computing--paradigms, methods, tools * Approximate reasoning * Probabilistic and statistical methods * Software tools, hardware implementation Stream3: Intelligent Information Systems and their Applications * Connectionist-based information systems * Hybrid systems * Expert systems * Adaptive systems * Machine learning, data mining and intelligent databases * Pattern recognition and image processing * Speech recognition and language processing * Intelligent information retrieval systems * Human-computer interfaces * Time-series prediction * Control * Diagnosis * Optimisation * Application of intelligent information technologies in: manufacturing, process control, quality testing, finance, economics, marketing, management, banking, agriculture, environment protection, medicine, geographic information systems, government, law, education, and sport * Intelligent information technologies on the global networks HONORARY CHAIR Shun-Ichi Amari, Tokyo University GENERAL CONFERENCE CHAIR Nikola Kasabov, University of Otago LOCAL ORGANIZING COMMITTEE CHAIR: Philip Sallis, University of Otago CONFERENCE ORGANISER Ms Kitty Ko Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand phone: +64 3 479 8153, fax: +64 3 479 8311, email: kittyko@commerce.otago.ac.nz CALL FOR PAPERS Papers must be received by 30 May 1997. They will be reviewed by senior researchers in the field and the authors will be informed about the decision of the review process by 20 July 1997. The accepted papers must be submitted in a camera-ready format by 20 August. All accepted papers will be published by IEEE Computer Society Press. As the conference is a multi-disciplinary meeting the papers are required to be comprehensible to a wider rather than to a very specialised audience. Papers will be presented at the conference either in an oral or in a poster session. Please submit three copies of the paper written in English on A4-format white paper with one inch margins on all four sides, in two column format, on not more than 4 pages, single-spaced, in Times or similar font of 10 points, and printed on one side of the page only. Centred at the top of the first page should be the complete title, author(s), mailing and e-mailing addresses, followed by an abstract and the text. In the covering letter the stream and the topic of the paper according to the list above should be indicated. The IEEE Transaction journals LaTex article style can be used. SPECIAL ISSUES OF JOURNALS AND EDITED VOLUMES Selected papers will be published in special issues of scientific journals. The organising committee is looking for publications of edited volumes which include chapters covering the conference topics written by invited conference participants. TUTORIALS (24 November) Conference tutorials will be organized to introduce the basics of cognitive modelling, dynamical systems, neural networks, fuzzy systems, evolutionary programming, soft computing, expert systems, hybrid systems, and adaptive systems. Proposals for tutorials are due on 30 May 1997. EXHIBITION Companies and university research laboratories are encouraged to exhibit their developed or distributing software and hardware systems. STUDENT SESSION Postgraduate students are encouraged to submit papers to this session following the same formal requirements for paper submission. The submitted papers will be published in a separate brochure. SPECIAL EVENTS FOR PRACTITIONERS The New Zealand Computer Society is organising special demonstrations, lectures and materials for practitioners working in the area of information technologies. VENUE (Dunedin/Queenstown) The Conference will be held at the University of Otago, Dunedin, New Zealand. The closing session will be held on Friday, 28 November on a cruise on one of the most beautiful lakes in the world, Lake Wakatipu. The cruise departs from the famous tourist centre Queenstown, about 300 km from Dunedin. Transportation will be provided and there will be a separate discount cost for the cruise. ACCOMMODATION Accommodation has been booked at St Margaret's College located right on the Campus and 10 minutes from downtown Dunedin. The College offers well equipped facilities including library, sport hall, music hall and computers with e-mail connection. Full board (NZ$50) is available during the conference days as well as two days before and after the conference. Accommodation is also available for a range of hotels in the city. TRAVELLING The Dunedin branch of House of Travel, a travelling company, is happy to assist in any domestic and international travelling arrangements for the Conference delegates. They can be contacted through email: travel@es.co.nz, fax: +64 3 477 3806, phone: +64 3 477 3464, or toll free number: 0800 735 737 (within NZ). POSTCONFERENCE EVENTS Following the closing conference cruise, delegates may like to experience the delights of Queenstown, Central Otago, and Fiordland. Travel plans can be coordinated by the Dunedin Visitor Centre (phone: +64 3 474 3300, fax: +64 3 474 3311). IMPORTANT DATES Papers due: 30 May 1997 Proposals for tutorials: 30 May 1997 Notification of acceptance: 20 July 1997 Final camera-ready papers due: 20 August 1997 Registration of at least one author of a paper: 20 August 1997 Early registration: 20 August 1997 CONFERENCE CONTACTS, PAPER SUBMISSIONS, CONFERENCE INFORMATION, REGISTRATION FORMS Conference Secretariat Department of Information Science, University of Otago, PO Box 56, Dunedin, New Zealand; phone: +64 3 479 8142; fax: +64 3 479 8311; email: iconip97@otago.ac.nz Home page: http://divcom.otago.ac.nz:800/com/infosci/kel/conferen.htm ---------------------------------------------- ICONIP'97 jointly with ANZIIS'97 and ANNES'97 TENTATIVE REGISTRATION PLEASE PRINT Title:________________________________ Surname:______________________________ First Name:___________________________ Position:_____________________________ Organisation:_________________________ Department:___________________________ Address:______________________________ ______________________________________ City:_________________________________ Country:______________________________ Phone:________________________________ Fax:__________________________________ Email:________________________________ Yes/No. Would you attend the conference? Yes/No. Would you submit a paper? Yes/No. Would you attend the closing session on the cruise? Yes/No. Would you like any further information? Please mail a copy of this completed form to: Ms Kitty Ko Department of Information Science University of Otago PO Box 56 Dunedin New Zealand. -------------------------------------------------------------- -------------------------------------------------------------------------------- Assoc.Professor Dr Nikola Kasabov phone:+64 3 479 8319 Director of Graduate Studies fax:+64 3 479 8311 Department of Information Science nkasabov@otago.ac.nz University of Otago P.O. Box 56, Dunedin, New Zealand home page http://divcom.otago.ac.nz:800/COM/INFOSCI/KEL/home.htm ------------------------------------------------------------------------------- From dhw@almaden.ibm.com Sat Aug 24 05:02:55 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 FAA27673 for ; Sat, 24 Aug 1996 05:02:46 -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 FAA29990 for ; Sat, 24 Aug 1996 05:02:45 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id ab10962; 24 Aug 96 0:30:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10940; 24 Aug 96 0:14:20 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa18630; 24 Aug 96 0:13:28 EDT Received: from EDRC.CMU.EDU by B.GP.CS.CMU.EDU id aa24169; 23 Aug 96 19:55:47 EDT Received: from ALMADEN.IBM.COM by EDRC.CMU.EDU id aa27068; 23 Aug 96 19:54:49 EDT Received: from ALMADEN by almaden.ibm.com (IBM VM SMTP V2R2) with BSMTP id 4367; Fri, 23 Aug 96 16:53:33 PDT Received: by ALMADEN (XAGENTA 4.0) id 9331; Fri, 23 Aug 1996 16:53:33 -0700 Received: by buson.almaden.ibm.com (AIX 4.1/UCB 5.64/4.03) id AA22322; Fri, 23 Aug 1996 16:54:39 -0700 Date: Fri, 23 Aug 1996 16:54:39 -0700 From: dhw@almaden.ibm.com MMDF-Warning: Parse error in original version of preceding line at DST.BOLTZ.CS.CMU.EDU Message-Id: <9608232354.AA22322@buson.almaden.ibm.com> To: Connectionists@cs.cmu.edu Subject: Job openings *** Job Announcements. Please distribute. *** The Web is currently dumb. Join our team at IBM net.Mining; we are making the web intelligent. We currently have immediate need to fill positions at our Almaden Research Center facility in the south of Silicon Valley. net.Mining is a sub-organization of IBM Data Mining Solutions, a rapidly expanding group that also has openings (see recent postings). IBM is an equal opportunity employer. Scientific Programmers/ Responsibilities: Interact with the Machine Learning Researchers to implement new web-based algorithms as code, verify the code, and test the algorithms in real world environments. Must be able to work independently. Qualitifications: Bachelors or equivalent in computer science, statistics, mathematics, physics, or an equivalent field. Higher degree highly desirable. Extensive experience implementing numeric code, especially in machine learning, statistics, neural nets, or a similar field. Familiarity with college-level mathematics (multi-variable calculus, differential equations, linear algebra, etc.) 2 or more years experience with C/C++ in a research or commercial environment. Knowledge of Internet technologies highly desirable. Machine Learning Researchers/ Responsibilities: Develop new algorithms applying machine learning and associated technologies to the web. Develop new such technologies. Work with the Scientific Programmers to implement and investigate those algorithms and technologies in the real world. Qualifications include: PhD or equivalent in computer science, statistics, mathematics, physics, or an equivalent field, with an emphasis on machine learning, statistics, neural nets, or a similar field. Strong background in mathematics. Experience with C/C++ highly desirable. Knowledge of information retrieval and/or indexing systems, text mining, and/or knowledge of Internet technologies, all highly desirable. From josh@vlsia.uccs.edu Sat Aug 24 06:01:13 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 GAA27836 for ; Sat, 24 Aug 1996 06:00:54 -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 GAA00233 for ; Sat, 24 Aug 1996 06:00:52 -0500 Received: from TELNET-1.SRV.CS.CMU.EDU by telnet-1.srv.cs.CMU.EDU id aa10962; 24 Aug 96 0:29:06 EDT Received: from DST.BOLTZ.CS.CMU.EDU by TELNET-1.SRV.CS.CMU.EDU id aa10935; 24 Aug 96 0:13:31 EDT Received: from DST.BOLTZ.CS.CMU.EDU by DST.BOLTZ.CS.CMU.EDU id aa18625; 24 Aug 96 0:12:39 EDT Received: from CS.CMU.EDU by B.GP.CS.CMU.EDU id aa24131; 23 Aug 96 19:52:54 EDT Received: from vlsia.uccs.edu by CS.CMU.EDU id aa21090; 23 Aug 96 19:51:47 EDT Received: by vlsia.uccs.edu (4.1/SMI-4.1) id AA02678; Fri, 23 Aug 96 17:52:30 MDT Date: Fri, 23 Aug 96 17:52:30 MDT From: Alspector Message-Id: <9608232352.AA02678@vlsia.uccs.edu> To: connectionists@cs.cmu.edu Subject: call for papers, IWANNT*97 Cc: josh@vlsia.uccs.edu CALL FOR PAPERS International Workshop on Applications of Neural Networks (and other intelligent systems) to Telecommunications (IWANNT*97) Melbourne, Australia June 9-11, 1997 Organizing Committee General Chair: Josh Alspector, U. of Colorado Program Chair: Rod Goodman, Caltech Publications Chair: Timothy X Brown, U. of Colorado Treasurer: Anthony Jayakumar, Bellcore Publicity: Atul Chhabra, NYNEX Lee Giles, NEC Research Institute Local Arrangements: Adam Kowalczyk, Telstra, Chair Michael Dale, Telstra Andrew Jennings, RMIT Maributu Palaniswami, U. of Melbourne Robert Slaviero, Signal Proc. Ass. (& local IEEE liason) Jacek Szymanski, Telstra Program Committee: Nader Azarmi, British Telecom Miklos Boda, Ericsson Radio Systems Harald Brandt, Ericsson Telecommunications Tzi-Dar Chiueh, National Taiwan U Bruce Denby, U of Versailles Simon Field, Nortel Francoise Fogelman, SLIGOS Marwan A. Jabri, Sydney Univ. Thomas John, SBC S Y Kung, Princeton University Tadashi Sone, ATR Scott Toborg, SBC TRI IEEE Liaison: Steve Weinstein, NEC Conference Administrator: Helen Alspector IWANNT Conference Administrator Univ. of Colorado at Col. Springs Dept. of Elec. & Comp. Eng. P.O. Box 7150 Colorado Springs, CO 80933-7150 (719) 593-3351 (719) 593-3589 (fax) neuranet@mail.uccs.edu Dear Colleague: You are invited to an international workshop on applications of neural networks and other intelligent systems to problems in telecommunica- tions and information networking. This is the third workshop in a series that began in Princeton, New Jersey on October 18-20, 1993. and continued in Stockholm, Sweden on May 22-24, 1995. This conference will be at the University of Melbourne on the Monday through Wednesday (June 9 - 11, 1997) just before the Australian Conference on Neural Networks (ACNN) which will be at the same location on June 11 - 13 (Wednesday - Friday). There will be a hard cover proceedings available at the workshop. There is further information on the IWANNT home page at: http://ece-www.colorado.edu/~timxb/iwannt.html Suggested topics include: Internet Services Intelligent Agents Database Mining Network Management ATM Networking Wireless Networks Modulation and Coding Techniques Congestion Control Adaptive Equalization Speech Recognition Security Verification Adaptive User Interfaces Language ID/Translation Multimedia Networking Information Filtering Dynamic Routing Propagation Path Loss Modeling Dynamic Frequency Allocation Software Engineering Telecom Market Prediction Fault Identification and Prediction Character Recognition Adaptive Control Data Compression Credit Management Customer Modeling Submissions: Please submit 6 copies of both a 50 word abstract and a 1000 word summary of your paper to arrive in Colorado, USA by Oct. 15, 1996. Mail papers to the conference administrator. Note the following dates: Tuesday, Oct. 15, 1996: Abstract, summary due. Monday, Nov. 25, 1996: Notification of acceptance Monday, Feb. 10, 1997: Camera Ready Copy Due I hope to see you at the workshop. Sincerely, Josh Alspector, General Chair ----------------------------------------------------------- REGISTRATION FORM ___________________________________________________________ International Workshop on Applications of Neural Networks (and other intelligent systems) to Telecommunications (IWANNT*97) Melbourne, Australia June 9-11, 1997 Name: Institution: Mailing Address: Telephone: Fax: E-mail: Make check ($400; $500 after May 1, 1997; $200 students) out to IWANNT*97. Please make sure your name is on the check. Registration includes breaks and proceedings available at the conference. Mail to: Helen Alspector IWANNT Conference Administrator Univ. of Colorado at Col. Springs Dept. of Elec. & Comp. Eng. P.O. Box 7150 Colorado Springs, CO 80933-7150 (719) 593-3351 (719) 593-3589 (fax) neuranet@mail.uccs.edu Site The conference will be held at the University of Melbourne. There are several good hotels within walking distance of the university. More information will be sent to registrants or upon request.