An associative memory model based on multiclass classification
Lists
Only you see this
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 hyperplane. In order to solve them, we propose approximate linear or quadratic programming problems by using L1 or L2 norms. Moreover, we extend the proposed model into a nonlinear model which uses the kernel function. Through some numerical experiments, we verified that the proposed model is effective in the storage capacity and the stability of stored prototypes.
BibTeX
@inproceedings{yagi2004associative,
author = {Yasushi Yagi and Keiji Tatsumi and Tetsuzo Tanino},
title = {{An associative memory model based on multiclass classification}},
booktitle = {Society},
year = {2004},
doi = {10.11499/sicep.2004.0\_16\_2},
}Loading related content...