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.
Associative Memory Model with Forgetting Process Using Nonmonotonic Neurons
Kazushi MIMURA Masato OKADA Koji KURATA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 1998/11/25
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
associative memory model, nonmonotonic neuron, forgetting process, storage capacity, SCSNA,
Full Text: PDF(516.2KB)>>
An associative memory model with a forgetting process a la Mezard et al. is investigated for a piecewise nonmonotonic output function by the SCSNA proposed by Shiino and Fukai. Similar to the formal monotonic two-state model analyzed by Mezard et al. , the discussed nonmonotonic model is also free from a catastrophic deterioration of memory due to overloading. We theoretically obtain a relationship between the storage capacity and the forgetting rate, and find that there is an optimal value of forgetting rate, at which the storage capacity is maximized for the given nonmonotonicity. The maximal storage capacity and capacity ratio (a ratio of the storage capacity for the conventional correlation learning rule to the maximal storage capacity) increase with nonmonotonicity, whereas the optimal forgetting rate decreases with nonmonotonicity.