THE EFFECT OF SENSORY INPUT ON TRAJECTORIES GENERATED BY RECURRENT NEURAL NETWORKS

Authors
  1. Barton, S.A.
Corporate Authors
Defence Research Establishment Suffield, Ralston ALTA (CAN)
Abstract
We show that the iterative signals generated by a simple recurrently connected network of only 3 sigmoidal nodes become stable, periodic or chaotic, depending on the magnitude of a global parameter (sigma) that controls the steepness of the node responses. High values of sigma produce chaotic signals, and low values lead to stable signals, i.e. unchanging from cycle to cycle. The transition from stability, through periodicity to chaos is shown to be consistent with Feigenbaum's model of critical nonlinear systems.
Report Number
DRES-589 —
Date of publication
01 Jan 1993
Number of Pages
55
DSTKIM No
93-01662
CANDIS No
129709
Format(s):
Hardcopy;Originator's fiche received by DSIS

Permanent link

Document 1 of 1

Date modified: