Noise Robust Gradient Descent Learning for Complex-Valued Associative Memory

Masaki KOBAYASHI  Hirofumi YAMADA  Michimasa KITAHARA  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E94-A   No.8   pp.1756-1759
Publication Date: 2011/08/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E94.A.1756
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Nonlinear Problems
Keyword: 
complex-valued neural networks,  associative memory,  gradient descent learning,  noise robustness,  

Full Text: PDF(286.3KB)>>
Buy this Article




Summary: 
Complex-valued Associative Memory (CAM) is an advanced model of Hopfield Associative Memory. The CAM is based on multi-state neurons and has the high ability of representation. Lee proposed gradient descent learning for the CAM to improve the storage capacity. It is based on only the phases of input signals. In this paper, we propose another type of gradient descent learning based on both the phases and the amplitude. The proposed learning method improves the noise robustness and accelerates the learning speed.