Presentation 2012-12-12
An Application of Dynamic Binary Networks: Learning of Switching Signals of Matrix Converters
Yuta Nakayama, 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 (DBNN) and its learning of periodic binary sequence. As an application of object, we study matrix AC/AC converter which is a representative power electronics circuit. We propose the learning of teacher signal corresponding to switching signals of the matrix converter. The learning algorithm uses the genetic algorithm (GA) whose chromosomes correspond to parameters of the network. We then consider learning process and confirm storage and stability of the teacher signal.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Binary Neural Networks / Dinamic Binary Neural Networks / Matrix Converter / Genetic Algorithm
Paper # NC2012-76
Date of Issue

Conference Information
Committee NC
Conference Date 2012/12/5(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Application of Dynamic Binary Networks: Learning of Switching Signals of Matrix Converters
Sub Title (in English)
Keyword(1) Binary Neural Networks
Keyword(2) Dinamic Binary Neural Networks
Keyword(3) Matrix Converter
Keyword(4) Genetic Algorithm
1st Author's Name Yuta Nakayama
1st Author's Affiliation Hosei University()
2nd Author's Name Toshimichi Saito
2nd Author's Affiliation Hosei University
Date 2012-12-12
Paper # NC2012-76
Volume (vol) vol.112
Number (no) 345
Page pp.pp.-
#Pages 6
Date of Issue