Presentation 2006-12-05
Memory Search by Parameter Dynamics in Chaotic Neural Network
Takayuki KAMEI, Toshiya IWAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Dynamical properties of the chaotic neural network are sensitive to system parameters. Stored patterns in the network are also considered system parameters, because synaptic weights are constituted from them. We perform numerical experiments of the auto-associative chaotic neural network model for both cases of correlated stored patterns and that uncorrelated stored patterns. The dependence of dynamical properties on both the correlation among stored patterns and parameters is investigated. Using the results, we propose a memory search model that distinguish known pattern from unknown pattern.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Chaos / Neural Network / Memory Search
Paper # NC2006-85
Date of Issue

Conference Information
Committee NC
Conference Date 2006/11/28(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) Memory Search by Parameter Dynamics in Chaotic Neural Network
Sub Title (in English)
Keyword(1) Chaos
Keyword(2) Neural Network
Keyword(3) Memory Search
1st Author's Name Takayuki KAMEI
1st Author's Affiliation Department of Computer Science, College of Engineering, Ninon University()
2nd Author's Name Toshiya IWAI
2nd Author's Affiliation Department of Computer Science, College of Engineering, Ninon University
Date 2006-12-05
Paper # NC2006-85
Volume (vol) vol.106
Number (no) 407
Page pp.pp.-
#Pages 6
Date of Issue