Digital neural network system based in new concepts on the recall phase dynamics

J. Carrabina, J. C. Calderon, F. Lisa, C. Perez, F. Garrido, N. Avellana, E. Valderrama

    Producció científica: Contribució a revistaArticleRecercaAvaluat per experts

    Resum

    In this paper we present an electronic system designed to emulate neural networks. Two major restrictions are assumed: discrete synapses (+1,0,-1) and threshold-type neurons. Drawbacks given by restrictions are solved with a more complex learning algorithm that maps real valued configurations for synapses into bipolar ones. The central unit of the system is an ASIC designed in accordance with a new sequential dynamics, which is faster and with better recall characteristics. As a result, the system designed has a fast recall phase and a large number of neurons. A handwritten OCR system is being designed. © 1992.
    Idioma originalAnglès
    Pàgines (de-a)89-92
    RevistaMicroprocessing and Microprogramming
    Volum34
    DOIs
    Estat de la publicacióPublicada - 1 de gen. 1992

    Fingerprint

    Navegar pels temes de recerca de 'Digital neural network system based in new concepts on the recall phase dynamics'. Junts formen un fingerprint únic.

    Com citar-ho