On the Dynamics and Applications of a Discrete Time Binary Neural Network with Time Delay

Article type: Research Article

Authors: Gardella, S. | Kumagai, T. | Hashimoto, R. | Wada, M.

Affiliations: MagneTek S.p.A., 52028 Terranuova-Avezzo, Italy | National Institute of Bioscience and Human-Technology (NIBH), AIST, MITI, 1-1 Higashi, Tsukuba, Ibaraki 305, Japan

Abstract: A model of a fully interconnected neural network composed of neurons having a refractory period and integrating the afferent signals is presented. A theoretical analysis of its dynamics is carried out, considering the general case with periodic input and output sequences from which a teaching algorithm for storing periodic sequences in the network is derived. Finally, the performances of the network are illustrated through a selected example and its potentialities, as well as its possible applications, are discussed.

DOI: 10.3233/IFS-1994-2302

Journal: Journal of Intelligent and Fuzzy Systems, vol. 2, no. 3, pp. 221-228, 1994