Journal of Bionic Engineering ›› 2022, Vol. 19 ›› Issue (1): 224-239.doi: 10.1007/s42235-021-00136-2

• • 上一篇    

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

Sen Tian1, Jin Zhang2,3,4, Xuanyu Shu1, Lingyu Chen2, Xin Niu5, You Wang6   

  1. 1 School of Mathematics and Statistics, Hunan Normal University, Changsha 410081, China  2 College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China  3 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China  4 Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310058, China  5 Science and Technology on Parallel and Distributed Laboratory, College of Computer, National University of Defense Technology, Changsha 410199, China  6 Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou 310027, China
  • 收稿日期:2021-07-09 修回日期:2021-11-08 接受日期:2021-11-16 出版日期:2022-01-10 发布日期:2022-02-20
  • 通讯作者: Jin Zhang E-mail:mail_zhangjin@163.com
  • 作者简介:Sen Tian1, Jin Zhang2,3,4, Xuanyu Shu1, Lingyu Chen2, Xin Niu5, You Wang6

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

Sen Tian1, Jin Zhang2,3,4, Xuanyu Shu1, Lingyu Chen2, Xin Niu5, You Wang6   

  1. 1 School of Mathematics and Statistics, Hunan Normal University, Changsha 410081, China  2 College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China  3 School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha 410114, China  4 Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310058, China  5 Science and Technology on Parallel and Distributed Laboratory, College of Computer, National University of Defense Technology, Changsha 410199, China  6 Key Laboratory of Industrial Control Technology, Institute of Cyber Systems and Control, Zhejiang University, Hangzhou 310027, China
  • Received:2021-07-09 Revised:2021-11-08 Accepted:2021-11-16 Online:2022-01-10 Published:2022-02-20
  • Contact: Jin Zhang E-mail:mail_zhangjin@163.com
  • About author:Sen Tian1, Jin Zhang2,3,4, Xuanyu Shu1, Lingyu Chen2, Xin Niu5, You Wang6

摘要: With the continuous deepening of Artifcial Neural Network (ANN) research, ANN model structure and function are improving towards diversifcation 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 evaluation 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.

关键词: Artifcial neural network (ANN), Back Propagation (BP) network, Deep Belief Network (DBN), LeNet5 network, Olfactory bionic model (KIII model), Small world, Chaos, Synchronous

Abstract: With the continuous deepening of Artifcial Neural Network (ANN) research, ANN model structure and function are improving towards diversifcation 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 evaluation 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.

Key words: Artifcial neural network (ANN), Back Propagation (BP) network, Deep Belief Network (DBN), LeNet5 network, Olfactory bionic model (KIII model), Small world, Chaos, Synchronous