For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Shift-Invariant Associative Memory Based on Homogeneous Neural Networks
Hiromi MIYAJIMA Noritaka SHIGEI Shuji YATSUKI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2005/10/01
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Nonlinear Theory and its Applications)
associative memory, shift-invariant, homogeneous neural networks, memory capacity,
Full Text: PDF(332.4KB)>>
This paper proposes homogeneous neural networks (HNNs), in which each neuron has identical weights. HNNs can realize shift-invariant associative memory, that is, HNNs can associate not only a memorized pattern but also its shifted ones. The transition property of HNNs is analyzed by the statistical method. We show the probability that each neuron outputs correctly and the error-correcting ability. Further, we show that HNNs cannot memorize over the number,, of patterns, where m is the number of neurons and k is the order of connections.