Pulse neural network neuron membrane voltage calculation method

Abstract

The invention provides a method for calculating neuron membrane voltage of a spiking neural network, and relates to the technical field of spiking neural networks, and the method comprises the steps: firstly, converting an input signal into a pulse sequence through employing a time coding method, selecting a Spike Response Model neuron model as a membrane voltage calculation model of a neuron non-nonstress time period of the spiking neural network, and carrying out the calculation of the membrane voltage of the spiking neural network; then establishing a membrane voltage model generated by pulse accumulation of the pre-synaptic neurons in the post-synaptic neuron non-stress period, and finally establishing a pulse neural network neuron membrane voltage calculation model to realize calculation of the post-synaptic neuron membrane voltage; according to the method, the accumulation of neuron input pulses before the non-stress period highlights is calculated, the loss of input information is made up, the method is applied to image processing, the loss of information is reduced, and the utilization rate of the input information is improved.

Description

technical field [0001] The invention relates to the technical field of impulse neural networks, in particular to a method for calculating the neuron membrane voltage of an impulse neural network. Background technique [0002] Deep learning has promoted the development of artificial intelligence technology and achieved remarkable results in many fields. However, in tasks with more uncertainty, spatial and temporal correlation, and generalization, such as semantic understanding, adaptive learning, associative memory, multimodal information processing, etc., deep learning is far less than the human brain. Therefore, although deep learning represents the current advanced technology in the field of artificial intelligence, it is still far from the ideal brain-like general intelligence goal, and there are still many intelligent problems that are difficult to solve. In addition, the deep learning model will have catastrophic forgetting during long-term learning. How to have the ab...

AI Technical Summary

Problems solved by technology

The neuron enters the refractory period after the pulse is sent out, and the neuron does not receive the pulse sent by the presynaptic neuron during the refractory period, which causes the loss of the input pulse, that is, the loss of information. In practical applications, this will lead to the loss of input information incomplete, which may affect the performance of the application

Images