DMCA
Switching in Self-Controlled Chaotic Neuromodules
BibTeX
@MISC{Stollenwerk_switchingin,
author = {Nico Stollenwerk and Frank Pasemann and Forschungszentrum Julich and D- Julich},
title = {Switching in Self-Controlled Chaotic Neuromodules},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The activity dynamics of recurrent neural networks can exhibit deterministic chaos due to the nonlinear transfer functions. Chaotic attractors are winded around infinitely many unstable periodic orbits. Each can be stabilized by a feedback control. In the present article we explore the flexibility of the chaotic dynamics of a recurrent neuromodule and construct a neural controller which is able to switch between several periodic patterns in two different ways: either deterministically by external inputs or spontaneously by dynamic noise. The chaotic attractor acts as an intermediate state between successively stabilized dynamic patterns. It has all the possible motions present, like an attentive state between different stimuli. in: Proceedings of World Congress on Neural Networks, San Diego, California, Sept. 15 - 18, 1996, INNS Press and Lawrence Erlbaum, New Jersey, 1966, pp. 680 - 684. 1 1 Introduction The important role of deterministically chaotic dynamics for all fie...
Keyphrases
self-controlled chaotic neuromodules chaotic dynamic important role external input world congress dynamic pattern present article chaotic attractor neural network different stimulus recurrent neuromodule different way dynamic noise san diego neural controller recurrent neural network attentive state inn press feedback control lawrence erlbaum activity dynamic intermediate state several periodic pattern many unstable periodic orbit deterministic chaos nonlinear transfer function chaotic attractor act new jersey possible motion
