Dynamical behavior of Neural networks with anti-symmetrical cyclic connections

Shinya Suenaga, Yoshihiro Hayakawa, Koji Nakajima

Research output: Contribution to journalArticlepeer-review

Abstract

We show that a unit-group, which represents a group of contiguous units with the same sign of output, is a dominant component for the dynamical behavior of a neural network with anti-symmetrical cyclic connections for the nearest neighbor connections and global connections. In transient state, it is shown that the unit-group has the dynamics such that the amount n of units which belong to the unit-group increases with time, and that the increasing rate of n decreases with increasing n. The dynamics cause the large difference of the number of limit-cycles between discrete and continuous time models. Additionally, the period of the limit-cycle depends on the size of the unit-groups. This dependency is obtained from computer simulations and two approximation methods. These approximations provide the lower and the upper bounds of the periods which depend on the gain of an activation function. Using these approximations, we also obtain detailed relations between a period and the other network parameters analytically.

Original languageEnglish
Pages (from-to)2775-2786
Number of pages12
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE89-A
Issue number10
DOIs
Publication statusPublished - 2006 Oct

Keywords

  • Limit cycles
  • Neural network

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Dynamical behavior of Neural networks with anti-symmetrical cyclic connections'. Together they form a unique fingerprint.

Cite this