NON-SUPERVISING LEARNING METHOD IN ARTIFICIAL NEURON NETWORK BASED ON MEMORY NANO-DEVICES AND ARTIFICIAL NEURON NETWORK USING THE METHOD

摘要

The present invention provides an unsupervised learning method implemented in an artificial neural network based on memristive devices. It involves increasing the conductance of a synapse when there is temporal overlap between a pre-synaptic pulse and a postsynaptic pulse and decreasing its conductance upon receipt of a post-synaptic pulse when there is no temporal overlap with a pre-synaptic pulse.