Optical character recognition method based on membrane voltage driven spiking neuron supervised learning model

Abstract

The invention discloses an optical character recognition method of a spiking neuron supervised learning model based on membrane voltage driving. The method comprises the steps of obtaining an opticalcharacter sample set, a phase encoding method is adopted, a pulse sequence of the phase encoding method is adopted, a spiking neuron supervised learning model based on membrane voltage driving is established and trained, and the trained spiking neuron supervised learning model is used for recognizing optical characters to be detected. According to the invention, a phase encoding method is adoptedto encode a pulse sequence; establishing a spiking neuron supervised learning model based on membrane voltage driving and carrying out training; and the trained spiking neuron supervised learning model is used to identify the optical character to be detected, so that the spiking neuron sequence learning efficiency is significantly improved, and the optical character recognition efficiency and accuracy are further improved.

Description

technical field [0001] The invention belongs to the technical field of optical character recognition, in particular to an optical character recognition method based on a membrane voltage-driven spiking neuron supervised learning model. Background technique [0002] Spiking neural networks have been widely used to solve classification problems. In most cases, the final decision of the computational model based on spiking neural network is based on the excitation time or frequency of a single pulse, but there are few classifications based on the similarity of the spiking neural network excitation pulse sequence. [0003] Traditional frequency-encoding-based neural networks assume that biological neurons perceive information through frequency-encoding. However, frequency-based encoding cannot effectively account for rapid visual, auditory and gustatory responses. Spike timing-based neural activity was successively found in different regions of the brain, including the retina,...

AI Technical Summary

Problems solved by technology

However, in fact, the synaptic weight of spiking neurons first affects the membrane voltage, and then affects the firing time of spiking neurons

Therefore, the adjustment of the weight through the pulse excitation time is indirect, which inevitably increases the difficulty of learning and reduces the efficiency and accuracy of learning.

Images