Molina, Christophe3, Hulle, Marc Van3, Rouat, Jean3, Adali, Tülay3, Douglas, Scott C.3
This proceeding contains refereed papers presented at the thirteenth IEEE Workshop on Neural Networks for Signal Processing (NNSP’2003), held at the Atria-Mercure Conference Center, Toulouse, France, September 17-19, 2003. The Neural Networks for Signal Processing Technical Committee of the IEEE Signal Processing Society organized the workshop with sponsorship of the Signal Processing Society and the co-operation of the IEEE Neural Networks Society. The IEEE Press published the previous twelve volumes of the NNSP Workshop proceedings in a hardbound volume. This year, the bound volume is to be published by IEEE following the workshop, and we are pleased to inaugurate a new CDROM electronic format, which maintains the same standard as the printed version and facilitates the reading and searching of the papers. In recent years, the field of neural networks has matured considerably in both methodology and real-world application domains and is widely entering into everyday solutions adopted by research and industry, going far beyond “traditional” neural networks and academic examples. As reflected in this collection, contemporary neural networks for signal processing combine many ideas from adaptive signal/image processing, machine learning, and statistics in order to solve complex real-world signal processing applications. This year, two topics attracting particular interest were presented at two special sessions; one on bioinformatics and a second one on space and aeronautics. High quality across such topical diversity can only be maintained through a rigorous and selective review process. This year, 149 full papers (10 pages) were submitted, out of which 88 (resulting in an acceptance rate of 59%) were selected for oral or poster presentation, after reviews by three referees for each. Following the cancellation of the ICASSP’03 IEEE conference, we have also accepted and included in the CDROM copy of the proceedings 17 papers for presentation from ICASSP’2003. We would like to thank the NNSP’2003 Technical Committee for taking the time to provide quality reviews. Special thanks also go to Dr. Bernard Michot of the Organizing Committee for his commitment, and the members of the PROGEP association, Florence Foucaud, Marlène Pauly and Vincent Gerbaud, for the handling of the workshop budget and registration. This year, the workshop featured research work in the areas of nonlinear signal processing, system identification, blind source separation, theory of neural networks, applications in image and video processing, speech processing, as well as implementation and other applications of neural networks. In addition to regular and special sessions, the NNSP’2003 Workshop was fortunate to have the participation of three companies - IBM Life Science, Research Systems Inc., and Spotfire - with stands presenting their products related to signal processing and neural networks. We are also grateful to the Toulouse City Council and to Sanofi-Synthelabo for their generous financial support. We would like to express our appreciation and gratitude to all these contributors. Our warmest, special thanks go to our organizers for the special sessions and plenary speakers: Dr. Edgardo Ferran of Sanofi-Synthelabo Recherche Labège (France), Professor Gérard Dreyfus of L’ESPCI, Paris (France), Professor Rita Casadio of University of Bologna (Italy), Professor Manuel Samuelides of Ecole Nationale Supérieure de l'Aéronautique et de l'Espace, Toulouse (France), and Professor Mahesan Niranjan of Sheffield University (UK). Continuing the tradition of paperless and easy communication, many of the details of the NNSP’2003 Workshop were handled electronically through the workshop webpage (http://isp.imm.dtu.dk/nnsp2003), which, among other features, included web-based submissions, review, and registration. Christophe Molina, Sanofi-Synthelabo Recherche, France Tülay Adali, University of Maryland, Baltimore County, USA Jan Larsen, Technical University of Denmark Marc Van Hulle, Katholieke Universiteit Leuven, Belgium Scott Douglas, Southern Methodist University, USA Jean Rouat, Université de Sherbrooke, Canada.
machine learning; bioinformatics; neural networks; signal processing