The Function Representation of Artificial Neural Network

08/27/2019

∙

by   Zhongkui Ma, et al.

∙

0

∙

share

This paper expresses the structure of the artificial neural network as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of the neural network can be represented by a simple function, and it is possible to find the mathematical solution of the ANN. Thus, it can be recognized that the current ANN can be placed in a larger and more reasonable framework. Perhaps all questions about ANN will be eliminated.