English

Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof

Optimization and Control 2007-05-24 v1 Dynamical Systems

Abstract

We address the important theoretical question why a recurrent neural network with fixed weights can adaptively classify time-varied signals in the presence of additive noise and parametric perturbations. We provide a mathematical proof assuming that unknown parameters are allowed to enter the signal nonlinearly and the noise amplitude is sufficiently small.

Keywords

Cite

@article{arxiv.0705.3370,
  title  = {Adaptive classification of temporal signals in fixed-weights recurrent neural networks: an existence proof},
  author = {Ivan Tyukin and Danil Prokhorov and Cees van Leeuwen},
  journal= {arXiv preprint arXiv:0705.3370},
  year   = {2007}
}

Comments

22 pages