摘要
Abstract
Unlike Artificial Neural Networks(ANN),Spiking Neural Networks(SNN),as a representative of the third generation of neural network technologies,perform computations based on biological neuron mechanisms,using sequences of spike signals to transmit information.This exhibits significant energy efficiency advantages and high-speed processing capabilities for massive data.However,due to the complex dynamics of spiking neurons and the non-differentiability of spike computations,the current direct training methods for SNNs are not very effective,hindering their widespread application.At present,converting high-precision ANN to SNN is consid-ered one of the most promising methods for generating SNN.However,mainstream ANN-to-SNN conversion methods have their limi-tations:first,they do not support negative spikes,making it difficult to represent negative spikes from dynamic vision sensor cameras;second,low latency and high precision cannot be achieved simultaneously during the conversion process.To address these issues,this paper proposes a novel spiking neuron that can represent the entire range of values,supporting both positive and negative values in tradi-tional ANN as well as the positive and negative polarities of DVS(Dynamic Vision Sensor)spikes.Additionally,this paper proposes a step-wise Leaky ReLU activation function and a regional convergence testing algorithm to achieve zero-error conversion from ANN to SNN.With these methods,we realize a high-precision,low-latency,and robust ANN-to-SNN conversion.Our method demonstrates outstanding performance on the CIFAR10 and CIFAR100 datasets.关键词
ANN转换SNN/阶梯式Leaky ReLU激活函数/区域收敛测试算法/全域表达/鲁棒性测试Key words
ANN-to-SNN conversion/stepwise Leaky ReLU activation function/regional convergence testing algorithm/globally repre-senting/robust test分类
计算机与自动化
