A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics

• 作者: Sen Tian Jin Zhang Xuanyu Shu Lingyu Chen Xin Niu You Wang
• 来源期刊: 仿生工程学报（英文版）
• 年，卷（期）: 2022,（1）
• 所属期刊栏目: RESEARCH ARTICLES
• 页码范围: 224-239
• 页数: 16页
• 语种: 英文

摘要

With the continuous deepening of Artificial Neural Network(ANN)research,ANN model structure and function are improv-ing towards diversification and intelligence.However,the model is more evaluated from the pros and cons of the problem-solving results and the lack of evaluation from the biomimetic aspect of imitating neural networks is not inclusive enough.Hence,a new ANN models evaluation strategy is proposed from the perspective of bionics in response to this problem in the paper.Firstly,four classical neural network models are illustrated:Back Propagation(BP)network,Deep Belief Network(DBN),LeNet5 network,and olfactory bionic model(KⅢ model),and the neuron transmission mode and equation,network structure,and weight updating principle of the models are analyzed qualitatively.The analysis results show that the KⅢ model comes closer to the actual biological nervous system compared with other models,and the LeNet5 network simulates the nervous system in depth.Secondly,evaluation indexes of ANN are constructed from the perspective of bionics in this paper:small-world,synchronous,and chaotic characteristics.Finally,the network model is quantitatively analyzed by evalu-ation indexes from the perspective of bionics.The experimental results show that the DBN network,LeNet5 network,and BP network have synchronous characteristics.And the DBN network and LeNet5 network have certain chaotic characteristics,but there is still a certain distance between the three classical neural networks and actual biological neural networks.The KⅢ model has certain small-world characteristics in structure,and its network also exhibits synchronization characteristics and chaotic characteristics.Compared with the DBN network,LeNet5 network,and the BP network,the KⅢ model is closer to the real biological neural network.