Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!ADS.COM!Vision-List-Request From: Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) Newsgroups: comp.ai.vision Subject: Vision-List delayed redistribution Message-ID: <8907150600.AA06897@deimos.ads.com> Date: 14 Jul 89 22:08:04 GMT Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: Vision-List@ADS.COM Distribution: inet Organization: The Internet Lines: 346 Approved: vision-list@ads.com Vision-List Digest Fri Jul 14 14:08:05 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Call for Papers: INNS/IEEE Conference on Neural Networks, Jan. 1990 Intensive summer school on statistical pattern recognition ---------------------------------------------------------------------- Date: 10 Jul 89 04:39:00 GMT From: lehr@isl.stanford.edu (Michael Lehr) Subject: Call for Papers: INNS/IEEE Conference on Neural Networks, Jan. 1990 Summary: Papers requested for joint neural net conference in Washington DC Keywords: conference, neural networks Organization: Stanford University EE Dept. CALL FOR PAPERS International Joint Conference on Neural Networks IJCNN-90-WASH DC January 15-19, 1990, Washington, DC The Winter 1990 session of the International Joint Conference on Neural Networks (IJCNN-90-WASH DC) will be held on January 15-19, 1990 at the Omni Shoreham Hotel in Washington, DC, USA. The International Neural Network Society (INNS) and the Institute of Electrical and Electronics Engineers (IEEE) invite all those interested in the field of neural networks to submit papers for possible publication at this meeting. Brief papers of no more than 4 pages may be submitted for consideration for oral or poster presentation in any of the following sessions: APPLICATIONS TRACK: * Expert System Applications * Robotics and Machine Vision * Signal Processing Applications (including speech) * Neural Network Implementations: VLSI and Optical * Applications Systems (including Neurocomputers & Network Definition Languages) NEUROBIOLOGY TRACK: * Cognitive and Neural Sciences * Biological Neurons and Networks * Sensorimotor Transformations * Speech, Audition, Vestibular Functions * Systems Neuroscience * Neurobiology of Vision THEORY TRACK: * Analysis of Network Dynamics * Brain Theory * Computational Vision * Learning: Backpropagation * Learning: Non-backpropagation * Pattern Recognition **Papers must be postmarked by August 1, 1989 and received by August 10, 1989 to be considered for presentation. Submissions received after August 10, 1989 will be returned unopened.** International authors should be particularly careful to submit their work via Air Mail or Express Mail to ensure timely arrival. Papers will be reviewed by senior researchers in the field, and author notifications of the review decisions will be mailed approximately October 15, 1989. A limited number of papers will be accepted for oral and poster presentation. All accepted papers will be published in full in the meeting proceedings, which is expected to be available at the conference. Authors must submit five (5) copies of the paper, including at least one in camera-ready format (specified below), as well as four review copies. Do not fold your paper for mailing. Submit papers to: IJCNN-90-WASH DC Adaptics 16776 Bernardo Center Drive, Suite 110 B San Diego, CA 92128 UNITED STATES (619) 451-3752 SUBMISSION FORMAT: Papers should be written in English and submitted on 8-1/2 x 11 inch or International A4 size paper. The print area on the page should be 6-1/2 x 9 inches (16.5 x 23 cm on A4 paper). All text and figures must fit into no more than 4 pages. The title should be centered at the top of the first page, and it should be followed by the names of the authors and their affiliations and mailing addresses (also centered on the page). Skip one line, and then begin the text of the paper. We request that the paper be printed by typewriter or letter-quality printer with clear black ribbon, toner, or ink on plain bond paper. We cannot guarantee the reproduction quality of color photographs, so we recommend black and white only. The type font should be Times Roman or similar type font, in 12 point type (typewriter pica). You may use as small a type as 10 point type (typewriter elite) if necessary. The paper should be single-spaced, one column, and on one side of the paper only. Fax submissions are not acceptable. **Be sure to specify which track and session you are submitting your paper to and whether you prefer an Oral or Poster presentation. Also include the name, complete mailing address and phone number (or fax number) of the author we should communicate with regarding your paper.** If you would like to receive an acknowledgment that your paper has been received, include a self-addressed, stamped post-card or envelope for reply, and write the title and authors of the paper on the back. We will mark it with the received date and mail it back to you within 48 hours of receipt of the paper. Submission of the paper to the meeting implies copyright approval to publish it as part of the conference proceedings. Authors are responsible for obtaining any clearances or permissions necessary prior to submission of the paper. ------------------------------ Date: 14 Jul 89 14:05:00 WET From: Josef Kittler Subject: Intensive summer school on statistical pattern recognition INTENSIVE SUMMER SCHOOL ON STATISTICAL PATTERN RECOGNITION 11-15 September 1989 University of Surrey PROGRAMME The course is divided into two parts: Course A The Fundamentals of Statistical Pattern Recognition Course B Contextual Statistical Pattern Recognition Course A will cover the basic methodology of statistical pattern recognition. Course B will feature a number of advanced topics concerned with the use of contextual information in pattern recognition, with a particular emphasis on Markov models in speech and images. Several example classes will be aimed at familiarizing the participants with the material presented. The course will include a seminar on application of pattern recognition methods to specific problems in which a step by step description of the design of practical pattern recognition systems will be outlined. Ample time will be devoted to discussion of algorithmic and practical aspects of pattern recognition techniques. COURSE A: THE FUNDAMENTALS OF STATISTICAL PATTERN RECOGNITION 11-13 September 1989 ELEMENTS OF STATISTICAL DECISION THEORY Model of pattern recognition system. Decision theoretic approach to pattern classification. Bayes decision rule for minimum loss and minimum error rate. Sequential and sequential compound decision theory. Optimum error acceptance tradeoff. Learning algorithms. NONPARAMETRIC PATTERN CLASSIFICATION The Nearest Neighbour (NN) technique: 1-NN, k-NN, (k,k')-NN pattern classifiers. Error acceptance tradeoff for nearest neighbour classifiers. Error bounds. Editing techniques. DISCRIMINANT FUNCTIONS Discriminant functions and learning algorithms. Deterministic learning. The least square criterion and learning scheme, relationship with the 1-NN classifier. Stochastic approximation. Optimization of the functional form of discriminant functions. ESTIMATION THEORY Probability density function estimation: Parzen estimator, k-NN estimator, orthogonal function estimator. Classification error rate estimation: resubstitution method, leave-one-out method, error estimation based on unclassified test samples. FEATURE SELECTION Concepts and criteria of feature selection, interclass distance measures, nonlinear distance metric criterion, probabilistic distance and dependence measures and their properties, probabilistic distance measures for parametric distributions, entropy measures (logarithmic entropy, square entropy, Bayesian distance), algorithms for selecting optimal and suboptimal sets of features, recursive calculation of parametric separability measures. Nonparametric estimation of feature selection criterion functions. FEATURE EXTRACTION Probabilistic distance measures in feature extraction, Chernoff parametric measure, divergence, Patrick and Fisher method. Properties of the Karhunen-Lo\`eve expansion, feature extraction techniques based on the Karhunen-Lo\`eve expansion. Nonorthogonal mapping methods, nonlinear mapping methods, discriminant analysis. CLUSTER ANALYSIS Concepts of a cluster, dissemblance and resemblance measures, globally sensitive methods, global representation of clusters by pivot points and kernels, locally sensitive methods (methods for seeking valleys in probability density functions), hierarchical methods, minimum spanning tree methods, clustering algorithms. *************************************************************************** COURSE B: CONTEXTUAL STATISTICAL PATTERN RECOGNITION 14-15 September 1989 INTRODUCTION The role of context in pattern recognition. Heuristic approaches to contextual pattern recognition. Labelling of objects arranged in networks (chains, regular and irregular lattices). Neighbourhood systems. Elements of compound decision theory. MODELS Markov chains. Causal and noncausal Markov random fields (MRF). Gibbs distributions. Hidden Markov chain and random field models for speech and images. Simulation of causal Markov processes. Simulation of noncausal MRF: The Metropolis algorithm. DISCRETE RELAXATION Compatibility coefficients. Concept of consistent labelling. Waltz discrete relaxation algorithm. Maximum aposteriori probability (MAP) of joint labelling. Viterbi algorithm for Markov chains, dynamic programming. Iterative algorithm for local MAP optimization in MRF. Geman and Geman Bayesian estimation by stochastic relaxation, simulated annealing. RECURSIVE COMPOUND DECISION RULES MAP of labelling individual objects. Filtering and fixed-lag smoothing in hidden Markov chains. Baum's algorithm. Labelling in hidden Markov meshes and in Pickard random fields. Unsupervised learning of underlying model parameters. PROBABILISTIC RELAXATION Problem specification. Combining evidence. Support functions for specific neighbourhood systems. Relationship with conventional compatibility and support functions (arithmetic average and product rule). Global criterion of ambiguity and consistency. Optimization approaches to label probability updating (Rosenfeld, Hummel and Zucker algorithm, projected gradient method). APPLICATIONS Speech recognition. Image segmentation. Scene labelling. Texture generation. ************************************************************************ GENERAL INFORMATION COURSE VENUE University of Surrey, Guildford, United Kingdom LECTURERS Dr Pierre DEVIJVER & Philips Research Laboratory, Avenue & Em Van Becelaere 2, B-1170 Brussels, Belgium Dr Josef KITTLER & Department of Electronic and Electri- & cal Engineering, University of Surrey, & Guildford GU2 5XH, England PROGRAMME SCHEDULE COURSE A will commence on Monday, September 11 at 10.00 a.m. (registration 9.00 - 10.00 a.m.) and finish on Wednesday, September 13 at 4 p.m. COURSE B will commence on Thursday, September 14 at 10.00 a.m. (registration 9.00 - 10.00 a.m.) and finish on Friday, September 15 at 4 p.m. ACCOMMODATION Accommodation for the participants will be available on the campus of the University for the nights of 10-14 September at the cost of 27.80 per night covering dinner, bed and breakfast. REGISTRATION AND FURTHER INFORMATION Address registration forms and any enquiries to Mrs Marion Harris, Department of Electronic and Electrical Engineering, University of Surrey, Guildford GU2 5XH, England, telephone 0483 571281 ext 2271. Rights reserved to cancel the course or change the programme if minimum numbers are not obtained or to limit participation according to capacity. All reservations handled on first-come first-served basis. WHO SHOULD ATTEND The course is intended for graduate students, engineers, mathematicians, computer scientists, applied scientists, medical physicists and social scientists engaged in work on pattern recognition problems of practical significance. In addition programmers and engineers concerned with the effective design of pattern recognition systems would also benefit. Applicants for COURSE A should have some familiarity with basic engineering mathematics and some previous exposure to probability and statistics. Applicants for COURSE B only should have working knowledge of basic statistical pattern recognition techniques. The material covered is directly relevant to applications in character recognition, speech recognition, automatic medical diagnosis, seismic data classification, target detection and identification, remote sensing, computer vision for robotics, and many other application areas. ------------------------------ End of VISION-LIST ********************