Presentation	2013-09-27 Dynamic Binary Neural Networks: Storing a Periodic Orbit and its Stabilization Ryota KOUZUKI, Toshimichi SAITO,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	This paper studies a dynamic binary neural networks characterized by signum activation function and ternary weighting parameters. In order to store and stabilize a desired periodic orbit, we consider simple learning algorithm. In the learning algorithm, the threshold parameters are determined theoretically. The weighting parameters are adjusted based on the genetic algorithm. We use a simple return map on the lattice points in order to visualize the basic dynamics of the network, such as periodic phenomena and its domain of attraction. Performing basic numerical experiments for an example teacher signal of a matrix converter, we have confirmed storage of desired periodic patterns and their stability.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Neural Network / Genetic Algorithm / Return Map
Paper #	CAS2013-44,NLP2013-56
Date of Issue

Conference Information
Committee	NLP
Conference Date	2013/9/19(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Nonlinear Problems (NLP)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Dynamic Binary Neural Networks: Storing a Periodic Orbit and its Stabilization
Sub Title (in English)
Keyword(1)	Neural Network
Keyword(2)	Genetic Algorithm
Keyword(3)	Return Map
1st Author's Name	Ryota KOUZUKI
1st Author's Affiliation	EE Dept., Hosei University()
2nd Author's Name	Toshimichi SAITO
2nd Author's Affiliation	EE Dept., Hosei University
Date	2013-09-27
Paper #	CAS2013-44,NLP2013-56
Volume (vol)	vol.113
Number (no)	225
Page	pp.pp.-
#Pages	5
Date of Issue