Presentation 2006-03-20
Development of a specified processor suited for GA-based learning to binary neural networks
Akio TAKAHASHI, Tatuya HIRANE, Hidehiro NAKANO, Arata MIYAUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a specified processor system suited for executing a GA-based learning method to Binary Neural Networks (BNNs). First, we explain specified instruction sets, overall architecture, and each processing unit in the processor. Next, we execute learning algorithms by using the proposed processor system and by using a general-purpose computer respectively. We then compare those execution time and learning performances. We show that the proposed processor system can perform much faster learning than the general-purpose computer.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Genetic Algorithm / Binary Neural Network / Processor System
Paper # NLP2005-145
Date of Issue

Conference Information
Committee NLP
Conference Date 2006/3/13(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) Development of a specified processor suited for GA-based learning to binary neural networks
Sub Title (in English)
Keyword(1) Genetic Algorithm
Keyword(2) Binary Neural Network
Keyword(3) Processor System
1st Author's Name Akio TAKAHASHI
1st Author's Affiliation Musashi Institute of Technology()
2nd Author's Name Tatuya HIRANE
2nd Author's Affiliation Musashi Institute of Technology
3rd Author's Name Hidehiro NAKANO
3rd Author's Affiliation Musashi Institute of Technology
4th Author's Name Arata MIYAUCHI
4th Author's Affiliation Musashi Institute of Technology
Date 2006-03-20
Paper # NLP2005-145
Volume (vol) vol.105
Number (no) 675
Page pp.pp.-
#Pages 6
Date of Issue