A Chaotic Memory Search Model Based on Associative Dynamics Using Features in Stored Patterns

Kunikazu Kobayashi; Kenji Watanabe; Masanao Obayashi

doi:10.11499/sicep.2002.0.680.0

SICE Annual Conference 2002

DOI https://doi.org/10.11499/sicep.2002.0.680.0

Conference information

Host: The Society of Instrument and Control Engineers

Co-host: IEEE/Industiral Electronic Society, IEEE/Robotics and Automation Society, IEEE/Control System Society

A Chaotic Memory Search Model Based on Associative Dynamics Using Features in Stored Patterns

Kunikazu Kobayashi, Kenji Watanabe, Masanao Obayashi

Author information

Keywords: Chaotic neural network, Memory search, Feature, Associative dynamics

CONFERENCE PROCEEDINGS FREE ACCESS

Pages 680

Details

Abstract

A new chaotic memory search model based on associative dynamics using features in stored patterns is proposed. In the present paper, two kinds of features are considered; external and internal ones. The former is assigned by a designer and the latter is automatically assigned by competitive learning. The control of chaotic and static states is realized using a presynaptic inhibition model. The performance of the proposed model is evaluated through computer simulation.

Corresponding author

Register with J-STAGE for free!