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.
Capacity of Second-Order Bidirectional Associative Memory with Finite Neuron Numbers
Yutaka KAWABATA Yoshimasa DAIDO Kaname KOBAYASHI Shimmi HATTORI
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1997/11/25
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
BAM, capacity, error probability, characteristic function, Hermite Gauss,
Full Text: PDF(493.1KB)>>
This paper describes relation between the number of library pairs and error probability to have all the pairs as fixed points for second-order bidirectional associative memory (BAM). To estimate accurate error probability, three methods have been compared; (a) Gaussian approximation, (b) characteristic function method, and (c) Hermite Gaussian approximation (proposed by this paper). Comparison shows that Gaussian approximation is valid for the larger numbers of neurons in both two layers than 1000. While Hermite Gaussian approximation is applicable for the larger number of neurons than 30 when Hermite polynomials up to 8th are considered. Capacity of second-order BAM at the fixed error probability is estimated as the function of the number of neurons.