Evaluation of a New Artificial Neural Network Model Combined with Bionics

Subjects: Computer Science >> Other Disciplines of Computer Science submitted time 2020-03-29

张锦 舒炫煜 黄昭彦 易胜

Abstract： The structure and function of artificial neural network model are developing towards diversification and intelligence. However, the researchers only evaluate the model from the result of solving the problem,which is unilateral.Therefore, in this paper, we propose to build an index set to evaluate the bionic degree of artificial neural network from the perspective of bionics.We uses quantitative methods to analyze the bionics of the model as a whole.In the determine the nature aspect, the neuron equation, network structure and weight renewal principle of the model are compared and analyzed;In the quantitative aspect,the index set is constructed based on the bionic point of view i.e. small world, synchronization and chaos, which is analyzed on the model.The analysis results show that the LeNet5 model and the BP neural network have synchronization characteristics, but they are still a certain distance from the real biological neural network, while the KIII model has certain small-world characteristics in structure, and its network also exhibits synchronization characteristics and chaos characteristics, which is Closer to the real biological neural network.

Peer Review Status:Awaiting Review

 Hits 12745  Downloads 2176  Comment