Presentation 1998/3/20
Dynamical Learning of Neural Network Based on Chaotic Dynamics
Kazuhiro KOJIMA, Koji ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A binary pattern learning model based on dynamical interaction with environments is proposed. The memory system in this model is composed of large and low degree of freedom modules. The former is associative memory, the latter is order variable. Evolutional equations for this system is derived from Lorentz equation. Computer simulations show following three matters. First, variety of output patterns can change, when a parameter of order variables changes in above equations. Second, the state of the system becomes"I don't know"state, when an unknown pattern is given to the system. Third, according to the progress of the learning, the state turns from a chaotic state to a periodic state. It means that a order is formed with the learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associative Memory / Chaotic Dynamics / Lorentz Equation / Order Variable
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/20(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) Dynamical Learning of Neural Network Based on Chaotic Dynamics
Sub Title (in English)
Keyword(1) Associative Memory
Keyword(2) Chaotic Dynamics
Keyword(3) Lorentz Equation
Keyword(4) Order Variable
1st Author's Name Kazuhiro KOJIMA
1st Author's Affiliation Department of Computational Intelligence and Systems Science Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology()
2nd Author's Name Koji ITO
2nd Author's Affiliation Department of Computational Intelligence and Systems Science Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology
Date 1998/3/20
Paper #
Volume (vol) vol.97
Number (no) 624
Page pp.pp.-
#Pages 8
Date of Issue