PERIODIC AND CHAOTIC SIGNAL GENERATION IN A RECURSIVE ARTIFICIAL NEURAL NETWORK

PDF

Authors
  1. Barton, S.A.
Corporate Authors
Defence Research Establishment Suffield, Ralston ALTA (CAN)
Abstract
The behaviour of artificial neural networks of recursive nonlinear processing elements can be rapidly moved from stability, through complex periodicity, to chaotic activity and back again, by only slight and subtle changes in a parameter that controls the steepness of the non-linear node response functions. The practical implications for artificial neural network applications, and the possible biological significance of this effect are discussed.
Report Number
DREA-TC-93-305-VOL-1-P-145 — @Conference Paper; CONTAINED IN 93-02664
Date of publication
01 Feb 1993
Number of Pages
26 (p145-170)
DSTKIM No
93-02656
CANDIS No
131312
Format(s):
Microfiche filmed at DSIS;Originator's fiche received by DSIS;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: