Cargando…

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

With the continuous deepening of Artificial Neural Network (ANN) research, ANN model structure and function are improving 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 biomimeti...

Descripción completa

Detalles Bibliográficos
Autores principales: Tian, Sen, Zhang, Jin, Shu, Xuanyu, Chen, Lingyu, Niu, Xin, Wang, You
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Singapore 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8674525/
https://www.ncbi.nlm.nih.gov/pubmed/34931121
http://dx.doi.org/10.1007/s42235-021-00136-2
_version_ 1784615685617352704
author Tian, Sen
Zhang, Jin
Shu, Xuanyu
Chen, Lingyu
Niu, Xin
Wang, You
author_facet Tian, Sen
Zhang, Jin
Shu, Xuanyu
Chen, Lingyu
Niu, Xin
Wang, You
author_sort Tian, Sen
collection PubMed
description With the continuous deepening of Artificial Neural Network (ANN) research, ANN model structure and function are improving 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 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.
format Online
Article
Text
id pubmed-8674525
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Springer Singapore
record_format MEDLINE/PubMed
spelling pubmed-86745252021-12-16 A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics Tian, Sen Zhang, Jin Shu, Xuanyu Chen, Lingyu Niu, Xin Wang, You J Bionic Eng Research Article With the continuous deepening of Artificial Neural Network (ANN) research, ANN model structure and function are improving 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 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. Springer Singapore 2021-12-16 2022 /pmc/articles/PMC8674525/ /pubmed/34931121 http://dx.doi.org/10.1007/s42235-021-00136-2 Text en © Jilin University 2021 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Research Article
Tian, Sen
Zhang, Jin
Shu, Xuanyu
Chen, Lingyu
Niu, Xin
Wang, You
A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title_full A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title_fullStr A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title_full_unstemmed A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title_short A Novel Evaluation Strategy to Artificial Neural Network Model Based on Bionics
title_sort novel evaluation strategy to artificial neural network model based on bionics
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8674525/
https://www.ncbi.nlm.nih.gov/pubmed/34931121
http://dx.doi.org/10.1007/s42235-021-00136-2
work_keys_str_mv AT tiansen anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT zhangjin anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT shuxuanyu anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT chenlingyu anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT niuxin anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT wangyou anovelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT tiansen novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT zhangjin novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT shuxuanyu novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT chenlingyu novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT niuxin novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics
AT wangyou novelevaluationstrategytoartificialneuralnetworkmodelbasedonbionics