Feedback type pulse neural network model training method for image data classification

Abstract

The invention discloses a feedback type pulse neural network model training method for image data classification. The method comprises the following steps: constructing a feedback type pulse neural network model, and training the model through implicit differential in an equilibrium state, the model comprising two spiking neuron models based on an integration activation model IF and a leakage integration activation model LIF, and a feedback type spiking neural network model of a single-hidden-layer neural network structure and a feedback type spiking neural network model of a multi-hidden-layer neural network structure; using re-parameterization method to restrain the spectral norm of the feedback connection weight, and using an improved method to carry out batch normalization. According to the invention, the common problem of difficulty in training of a spiking neural network model can be avoided, the method is used for high-performance and efficient classification processing of computer image data and neuromorphic image visual data in an energy-saving manner, and higher classification accuracy can be obtained with fewer neurons, smaller parameters and shorter time steps.

Description

technical field [0001] The invention belongs to the technical fields of pattern recognition, machine learning, artificial intelligence, image processing and neuromorphic computing, and relates to a computer image data classification method and a neuromorphic image visual data classification method, in particular to an image and neuromorphic data classification method Feedback spiking neural network model training method. Background technique [0002] In recent years, spiking neural network (SNN) models have received increasing attention due to their computationally energy-efficient properties in the task of image data classification. Inspired by the real neurons in the human brain, the neurons of the biologically feasible SNN model transmit information by sending out pulse signals, thereby supporting event-based computing, which can pass fewer energy consumption to achieve. The SNN model can process computer image data, and can also efficiently process neuromorphic image v...

AI Technical Summary

Problems solved by technology

However, they simply assume that the activation function of neurons is linear, and the model requires a large number of time steps to achieve good results on simple tasks

Images