Neuromorphic visual target classification system based on input weighted spiking neural network

Abstract

The invention discloses a neuromorphic visual target classification system based on an input weighted spiking neural network, and belongs to the technical field of artificial neural networks, and the classification system is composed of the following four method modules: a data preprocessing module, a network construction module, a learning module and an inference module. The data preprocessing module is used for converting the acquired event camera asynchronous output space-time pulse event flow into an event frame sequence; the network construction module is used for constructing the input weighting unit and the spiking neural layer unit into an input weighting spiking neural network according to a certain network connection mode; the learning module is used for learning the input weighted spiking neural network obtained by the network construction module according to the event frame sequence obtained by the preprocessing module, and generating a model file; and the inference module is used for loading the network model file output by the learning module to perform feedforward network calculation. According to the invention, the neuromorphic visual classification spiking neural network can maintain relatively high performance while having low time delay.

Description

technical field [0001] The invention belongs to the field of deep learning in machine learning, and in particular relates to a neuromorphic visual target classification system based on an input weighted impulse neural network. Background technique [0002] Event cameras are asynchronous neuromorphic vision sensors that generate a paradigm shift in the way visual information is acquired. Unlike traditional vision sensors that sample light at a fixed time, event cameras sample light dynamically according to the scene, and generate a pulse event stream by asynchronously measuring the brightness change of each pixel. Change polarity to encode. Spiking Neural Networks (SNNs) is a new generation of artificial neural networks inspired by the operating mechanism of the brain, using pulse sequences as the form of data transmission. Compared with traditional Artificial Neural Networks (ANNs), it has ultra-low time The advantages of delay and low energy consumption. The high time re...

AI Technical Summary

Problems solved by technology

However, this method does not distinguish the input of the network, which will affect the performance of the network to a certain extent.

In fact, the input at different moments contains different signal-to-noise ratios, and giving the same input weight to all input moments makes the network's ability to extract effective spatiotemporal features weaker.

Images