Presentation 2007-04-25
Analysis on network structures of neural networks with STDP learning
Hideyuki KATO, Tohru IKEGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, it has been reported that neural networks self-organize to produce functional complex networks using the Spike Timing Dependent synaptic Plasticity (STDP). The functional complex networks mean small-world networks and scale-free networks. However, experimental conditions used in the previous reports are not physiologically reasonable. In addition, although there are two kinds of learning rules in the STDP, additive and multiplicative, no reports have clarified how these two types are related, and what are different points between these two types of learning. Thus, in this report, we analysed the neural network structures using two kinds of the STDP learning rules with experimental conditions is physiologically valid. We show that a neural network with the multiplicative STDP learning rule evolves to a more small-world network than the additive one.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) STDP learning rule / neural networks / network structure
Paper # NLP2007-3
Date of Issue

Conference Information
Committee NLP
Conference Date 2007/4/18(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) Analysis on network structures of neural networks with STDP learning
Sub Title (in English)
Keyword(1) STDP learning rule
Keyword(2) neural networks
Keyword(3) network structure
1st Author's Name Hideyuki KATO
1st Author's Affiliation Graduate School of Science and Engineering, Saitama University()
2nd Author's Name Tohru IKEGUCHI
2nd Author's Affiliation Graduate School of Science and Engineering, Saitama University
Date 2007-04-25
Paper # NLP2007-3
Volume (vol) vol.107
Number (no) 21
Page pp.pp.-
#Pages 6
Date of Issue