HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Google Scholar Articles by Tyukin, I. Y. Articles by van Leeuwen, C. PubMed Articles by Tyukin, I. Y. Articles by van Leeuwen, C.

Adaptive Classification of Temporal Signals in Fixed-Weight Recurrent Neural Networks: An Existence Proof

I.Tyukin{at}le.ac.uk Department of Mathematics, School of Mathematics and Computer Science, University of Leicester, Leicester, LE1 7RH, U.K., and Laboratory for Perceptual Dynamics, Brain Science Institute, RIKEN, Wako-shi, Saitama, 351-0198, Japan

Danil Prokhorov

dvprokhorov{at}gmail.com Toyota Technical Center, Ann Arbor, MI 48105, U.S.A.

Cees van Leeuwen

ceesvl{at}brain.riken.jp Laboratory for Perceptual Dynamics, Brain Science Institute, RIKEN, Wako-shi, Saitama, 351-0198, Japan

Recurrent neural networks with fixed weights have been shown in practice to successfully classify adaptively signals that vary as a function of time in the presence of additive noise and parametric perturbations. We address the question: Can this ability be explained theoretically? We provide a mathematical proof that these networks have this ability even when parametric perturbations enter the signals nonlinearly. The restrictions that we impose on the signals to be classified are that they satisfy an assumption of nondegeneracy and that noise amplitude is sufficiently small. Further, we demonstrate that the recurrent neural networks may not only classify uncertain signals adaptively but also can recover the values of uncertain parameters of the signals, up to their equivalence classes.