Presentation 2007-11-18
Digital MLP with binary connection parameter and it's application
Toru ABE, Toshimichi SAITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies Digital Multi-Layer Perceptron (DLP) characterized by signum activation function and binary connection parameters. The DLP can realize various Boolean functions provided a sufficient number of hidden neurons are used. As a typical example, rules of Binary Cellular Automata (BCA) are used as teacher signals. Applying a simple algorithm, the DLP can learn the rules and can be a robust system than the original ruletable. Performing numerical experiments, we have given basic information for application to spatiotemporal pattern prediction problems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Digital Multi-Layer Perceptron / Binary Cellular Automaton / robust system / spatiotemporal pattern prediction
Paper # NC2007-59
Date of Issue

Conference Information
Committee NC
Conference Date 2007/11/11(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) Digital MLP with binary connection parameter and it's application
Sub Title (in English)
Keyword(1) Digital Multi-Layer Perceptron
Keyword(2) Binary Cellular Automaton
Keyword(3) robust system
Keyword(4) spatiotemporal pattern prediction
1st Author's Name Toru ABE
1st Author's Affiliation Department of electronics, Electrical and Computer Engineering, Hosei University()
2nd Author's Name Toshimichi SAITO
2nd Author's Affiliation Department of electronics, Electrical and Computer Engineering, Hosei University
Date 2007-11-18
Paper # NC2007-59
Volume (vol) vol.107
Number (no) 328
Page pp.pp.-
#Pages 5
Date of Issue