Computational Finance
   Hybrid Systems
   Recurrent Networks
   Support Vector Machines
   Input Variable Selection
   Classification Methods

   Book Chapters
   Journal Papers
   Conference Papers

   Windale Technologies


   Contact Me
View Andrew Back's profile on LinkedIn

   NIPS 94 Workshop

Neural Networks for Nonlinear Signal Processing

Andrew D. Back
Department of Electrical and Computer Engineering,
University of Queensland,
Brisbane, Qld 4072. Australia

Eric A. Wan
Department of Electrical Engineering and Applied Physics
Oregon Graduate Institute of Science and Technology

P.O. Box 91000, Portland, Oregon, 97291. USA.

A Postscript summary of workshop is available for downloading.

Workshop Abstract

Nonlinear signal processing using neural network models is a topic of recent interest in various application areas. Recurrent networks offer a potentially rich and powerful modelling capability though may suffer from some problems in training. On the other hand, simpler network structures which have an overall feedforward structure, but draw more strongly on linear signal processing approaches have been proposed. The resulting structures can be viewed as a nonlinear generalizations of linear filters. This workshop is aimed at addressing issues surrounding networks which may be viewed in a nonlinear signal processing framework, focussing in particular on those which employ some form of time delay connections and generally limited recurrent connections. We intend to consolidate some of the recent theoretical and practical results, as well as addressing open issues.


  1. "Computational Capabilities of Local-Feedback Recurrent Networks"
    Paolo Frasconi
    University of Florence, Italy
  2. Issues in Representation: Recurrent Networks as Sequential Machines
    C. Lee Giles and B.G. Horne
    NEC Research Institute
  3. "Properties of Recursive Memory Structures"
    Jose C. Principe
    University of Florida
  4. "A Local Model Net Approach to Modeling Nonlinear Dynamic Systems"
    Roderick Murray-Smith
  5. "A Spatio-Temporal Approach to Visual Pattern Recognition"
    Lokendra Shastri
  6. "The Performance of Recurrent Networks for Classifying Time-Varying Patterns"
    Tina Burrows and Mahesan Niranjan
    Cambridge University Engineering Department
  7. "Nonlinear Infomax With Adaptive Time Delays"
    Tony Bell
    The Salk Institute
  8. "The Sinc Tensor Product Network"
    Jerome Soller
    University of Utah
  9. "Discriminating Between Mental Tasks Using a Variety of EEG Representations"
    Chuck Anderson
    Colorado State University




Home   Research  Contact Me  Feedback  Publications

Copyright 1989-2008 Andrew Back. All Rights Reserved.