METHOD FOR GENERATING SPIKING NEURAL NETWORK BASED ON BURST SPIKES AND INFERENCE APPARATUS BASED ON SPIKING NEURAL NETWORK

摘要

The spike-based spiking neural network generating method includes mapping a weight of an artificial neural network model trained by a computer device to a spiking neural network (SNN) and optimizing the SNN to which the computer device is mapped. The optimizing step adjusts a threshold value for determining utterance according to the neuron state of the SNN.