Understanding Forward Process of Convolutional Neural Network

TL;DR

This paper investigates the forward processing in CNNs, revealing how activation functions act as rotation discriminators that help distinguish inputs, and draws parallels between neural networks and human brain data processing.

Contribution

It introduces a novel perspective on CNNs' forward process by analyzing activation functions as mechanisms for rotation and statistical differentiation, linking artificial and biological data processing.

Findings

Activation functions serve as rotation discriminators in CNNs.

CNNs distinguish inputs based on statistical indicators.

Artificial neural networks show similar data processing patterns to the human brain.

Abstract

This paper reveal the selective rotation in the CNNs' forward processing. It elucidates the activation function as a discerning mechanism that unifies and quantizes the rotational aspects of the input data. Experiments show how this defined methodology reflects the progress network distinguish inputs based on statistical indicators, which can be comprehended or analyzed by applying structured mathematical tools. Our findings also unveil the consistency between artificial neural networks and the human brain in their data processing pattern.