西华大学学报（自然科学版）2025，Vol.44Issue(6)：28-36,9.DOI:10.12198/j.issn.1673-159X.5230
基于Hopfield神经网络联想记忆的相似模式识别
Similar Pattern Recognition Based on Hopfield Neural Network Associative Memory
摘要
Abstract
The associative memory function of discrete Hopfield neural network is widely used in the field of pattern recognition because of its great fault tolerance.In this paper,for the crosstalk problem between similar memory samples in the associative memory of discrete Hopfield neural network,an im-proved Hopfield neural network associative memory pattern recognition algorithm is proposed based on neuron excitation threshold adjustment.Besides,the fault tolerance and real-time performance of the pro-posed algorithm are verified through the recognition of similar speed limit traffic sign images.The simula-tion results show that the correct recognition rate can still reach more than 90%when the pattern to be re-cognized is contaminated by noise to the extent of 50%.It follows the simulation results that it has the abil-ity to recognize incomplete input patterns and has good real-time performance.Therefore,the improved al-gorithm proposed in this paper can effectively recognize similar memory samples in the process of associat-ive memory.关键词
离散型Hopfield神经网络/神经元阈值/联想记忆/模式识别/相似交通标志Key words
discrete Hopfield neural network/neuronal threshold/associative memory/pattern recognition/similar traffic signs分类
信息技术与安全科学引用本文复制引用
徐晓惠,杨皓麟,杨继斌..基于Hopfield神经网络联想记忆的相似模式识别[J].西华大学学报（自然科学版）,2025,44(6):28-36,9.基金项目
四川省科技计划项目(2023YFG0068,2023YFG0067). （2023YFG0068,2023YFG0067）
