集成电路与嵌入式系统2025，Vol.25Issue(11)：24-30,7.DOI:10.20193/j.ices2097-4191.2025.0076
基于多值脉冲神经网络的目标位置识别算法
Object detection algorithm based on three-valued spike neural network
摘要
Abstract
As a representative method of neural morphological computing,spiking neural networks(SNNs)have been widely used in va-rious perception and control tasks,and software-hardware collaborative computing.However,the traditional Leaky Integrate and Fire(LIF)neural model widely is used in SNN can only encode input features as binary pulse signals,which severely limits its feature ex-pression ability and performance in complex visual tasks such as object detection.This article proposes a pulse neural network with a ternary activation layer based on a multi valued logic neuron model.By modifying the activation range within the convolutional layers,the ternary activation layer can significantly improve the model performance of object detection algorithms on the basis of binary activa-tion.The experiment results on public datasets show that the proposed method of ternary activation can improve the average precision(AP)across three types of traffic signs from 80.8％to 92.5％compared with binary activation.In addition,in order to run the above spike neural network in a multi value logic computing system based on novel nano-devices,we also evaluate the performance of the model after parameter quantification.The results show that after quantifying the model parameters to the integer range,the performance of the model only decreased by more than 1％.Compared with ANN,while the accuracy decreases by 4.2％,the number of parameters de-creases by 81.6％.关键词
脉冲神经网络/多值逻辑/目标检测/交通标志识别/人工智能Key words
spike neural network/multi-valued logic/object detection/traffic sign recognition/artificial intelligence分类
计算机与自动化引用本文复制引用
王明辉,魏熠民,王宇飞,杨智杰,赵静月,徐实,王蕾,龚锐..基于多值脉冲神经网络的目标位置识别算法[J].集成电路与嵌入式系统,2025,25(11):24-30,7.基金项目
基于新型纳米器件的多值逻辑计算系统结构研究(31511090203) （31511090203）
