Presentation 2010-11-20
An Approach to Logical Synthesis by Binary Neural Networks
Yuta NAKAYAMA, Ryo ITO, Toshimichi SAITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies a genetic-algorithm-based learning of binary neural networks (BNN) and its realization function of Boolean functions. We have two important results. First, the BNN can be equivalent to the minimum logical-sum form: the learning algorithm can be used as fast logical synthesis. Second, the BNN can realize a class of Boolean functions with smaller number of terms (hidden neurons) than that by the Quine-McCluskey algorithm: the learning algorithm may be developed into an effective logical synthesis methods. Performing typical numerical experiment, the algorithm efficiency is confirmed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Binary Neural networks / Genetic algorithm / Logic synthesis
Paper # NLP2010-108
Date of Issue

Conference Information
Committee NLP
Conference Date 2010/11/12(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) An Approach to Logical Synthesis by Binary Neural Networks
Sub Title (in English)
Keyword(1) Binary Neural networks
Keyword(2) Genetic algorithm
Keyword(3) Logic synthesis
1st Author's Name Yuta NAKAYAMA
1st Author's Affiliation Department of Electrical and Electronics Engineering, Hosei University()
2nd Author's Name Ryo ITO
2nd Author's Affiliation Department of Electrical and Electronics Engineering, Hosei University
3rd Author's Name Toshimichi SAITO
3rd Author's Affiliation Department of Electrical and Electronics Engineering, Hosei University
Date 2010-11-20
Paper # NLP2010-108
Volume (vol) vol.110
Number (no) 299
Page pp.pp.-
#Pages 5
Date of Issue