SPATIO-TEMPORAL PATTERN RECOGNITION USING A SPIKING NEURAL NETWORK AND PROCESSING THEREOF ON A PORTABLE AND/OR DISTRIBUTED COMPUTER

摘要

A system and method for characterizing a pattern, in which a spiking neuralnetwork having at least one layer of neurons is provided. The spiking neuralnetwork has a plurality of connected neurons for transmitting signals betweenthe connected neurons. A model for inducing spiking in the neurons isspecified. Each neuron is connected to a global regulating unit fortransmitting signals between the neuron and the global regulating unit. Eachneuron is connected to at least one other neuron for transmitting signals fromthis neuron to the at least one other neuron, this neuron and the at least oneother neuron being on the same layer. Spiking of each neuron is synchronizedaccording to a number of active neurons connected to the neuron. At least onepattern is submitted to the spiking neural network for generating sequences ofspikes in the spiking neural network, the sequences of spikes (i) beingmodulated over time by the synchronization of the spiking and (ii) beingregulated by the global regulating unit. The at least one pattern ischaracterized according to the sequences of spikes generated in the spikingneural network.