Presentation 2014-12-13
A Learning Method for Extended SpikeProp without Redundant Spikes : A Discussion on Time Delay
Takashi MATSUMOTO, Haruhiko TAKASE, Hiroharu KAWANAKA, Shinji TSURUOKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) SpikeProp, which is proposed by Booij, is a kind of spiking neural networks. It can learn the timing of output spikes, but cannot adjust the number of output spikes. Our research group has discussed the problem and proposed a learning method that can adjust both timing and number of spikes. However, its learning performance depends on the initial network structure (the number of hidden units, time delay, the number of sub-connections, and so on). In this article, we discuss the problem, especially the dependency to time delay. And, we proposed the method that removes connections that have unnecessary time delay during its training. The method dissolved the dependency for a simple benchmark problem.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Spiking Neural Network / SpikeProp / Time Series Imformation Processing / Learning Algorithm
Paper # NC2014-52
Date of Issue

Conference Information
Committee NC
Conference Date 2014/12/6(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) A Learning Method for Extended SpikeProp without Redundant Spikes : A Discussion on Time Delay
Sub Title (in English)
Keyword(1) Spiking Neural Network
Keyword(2) SpikeProp
Keyword(3) Time Series Imformation Processing
Keyword(4) Learning Algorithm
1st Author's Name Takashi MATSUMOTO
1st Author's Affiliation Graduate School of Engineering, Mie University()
2nd Author's Name Haruhiko TAKASE
2nd Author's Affiliation Graduate School of Engineering, Mie University
3rd Author's Name Hiroharu KAWANAKA
3rd Author's Affiliation Graduate School of Engineering, Mie University
4th Author's Name Shinji TSURUOKA
4th Author's Affiliation Graduate School of Regional Innovation Studies, Mie University
Date 2014-12-13
Paper # NC2014-52
Volume (vol) vol.114
Number (no) 362
Page pp.pp.-
#Pages 5
Date of Issue