Accession Number : ADD017317
Title : Digitally Weighted Neuron for Artificial Neural Network.
Descriptive Note : Patent, filed 28 May 93, Patented 27 Sep 94,
Corporate Author : DEPARTMENT OF THE NAVY WASHINGTON DC
Personal Author(s) : Swenson, Richard M ; Cole, John C , III ; Holmes, Steve L ; Ekas, Paul B
Report Date : 27 Sep 1994
Pagination or Media Count : 17
Abstract : A neuron for an artificial neural network provides digital weighting of input signals at a common portion of the neuron rather than at each synapse. The neuron is adapted for use of differential signals, and the weighting may be provided by field effect transistors of different widths, by subtracting a plurality of differential signal components from an opposite most significant component, or by subtracting one half of a differential signal component from the opposite next most significant component. The neuron may provide binary sign selection and digit selection by switching input and reference signals at each synapse.
Descriptors : *NEURAL NETS, *PATTERN RECOGNITION, *SYNAPSE, *PATENTS, INPUT, DIGITAL SYSTEMS, FIELD EFFECT TRANSISTORS, WEIGHTING FUNCTIONS, SIGNALS, NERVE CELLS, SWITCHING, SELECTION
Subject Categories : Electrical and Electronic Equipment
Anatomy and Physiology
Distribution Statement : APPROVED FOR PUBLIC RELEASE