An associative memory model based on multiclass classification

Yoshiyuki Yagi; Keiji Tatsumi; Tetsuzo Tanino

doi:10.11499/sicep.2004.0_16_2

SICE Annual Conference 2004

DOI https://doi.org/10.11499/sicep.2004.0_16_2

Conference information

Host: The Society of Instrument and Control Engineers

Co-host: The IEEE Industrial Electronics Society, The IEEE Robotics and Automation Society, The IEEE Control Systems Society, The IEEE Systems, Man and Cybernetics Society, The Instrumentation, Systems, and Automation Society

An associative memory model based on multiclass classification

Yoshiyuki Yagi, *Keiji Tatsumi, Tetsuzo Tanino

Author information

CONFERENCE PROCEEDINGS FREE ACCESS

Pages 16

Details

Abstract

The associative memory can be regarded as a multiclass classification problem. Thus, we formulate it as optimization problems to maximize Hamming distances between each prototype and a separate hyper plane. To solve them, we propose some approximate optimization problems by using L1 or L2 norms. Moreover, we extend the proposed model into a nonlinear model which uses the kernel function. Through numerical experiments, we verified that the proposed model is effective in the storage capacity and the stability of stored prototypes.

Corresponding author

Register with J-STAGE for free!