Robust neural temporal encoding for the memory using the oscillation, learning, and cell recruitment methods and apparatus

摘要

PROBLEM TO BE SOLVED: To provide a method for distinguishing temporal patterns and not merely coincidence of inputs or order of inputs, the method being consistent but reduced in complexity and including coding, decoding, recognizing and learning temporal spike signal patterns, by extensions to a scalable temporal neural model for robustness, confidence or integrity coding, and recruitment of cells for efficient temporal pattern memory.SOLUTION: A method comprises: providing a neuron circuit of a network with synaptic inputs, each associated with a synaptic weight of synaptic weights and a time delay; latching each of the synaptic inputs being weighted and delayed, upon a rise in an input of the neuron circuit comprising the synaptic inputs; and, upon the input or upon the neuron circuit spiking based on the rise in the input, applying a learning rule to the latched synaptic inputs to determine a change in the synaptic weight associated with that synaptic input.SELECTED DRAWING: Figure 15