
For FullText PDF, please login, if you are a member of IEICE,
or go to Pay Per View on menu list, if you are a nonmember of IEICE.

Simple Feature Quantities for Analysis of Periodic Orbits in Dynamic Binary Neural Networks
Seitaro KOYAMA Shunsuke AOKI Toshimichi SAITO
Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Vol.E101A
No.4
pp.727730 Publication Date: 2018/04/01
Online ISSN: 17451337 Type of Manuscript: LETTER Category: Nonlinear Problems Keyword: dynamic binary neural network, stability, sparsity,
Full Text: PDF(2.4MB) >>Buy this Article  Errata[Uploaded on April 5,2018]
Summary:
A dynamic neural network has ternary connection parameters and can generate various binary periodic orbits. In order to analyze the dynamics, we present two feature quantities which characterize stability and transient phenomenon of a periodic orbit. Calculating the feature quantities, we investigate influence of connection sparsity on stability of a target periodic orbit corresponding to a circuit control signal. As the sparsity increases, at first, stability of a target periodic orbit tends to be stronger. In the next, the stability tends to be weakened and various transient phenomena exist. In the most sparse case, the network has many periodic orbits without transient phenomenon.

