Understanding Forward Process of Convolutional Neural Network
This provides insights into CNN interpretability for researchers, though it appears incremental in explaining known mechanisms.
The paper investigates the forward process of convolutional neural networks (CNNs), revealing that activation functions act as a selective rotation mechanism that quantizes rotational aspects of input data, and finds consistency between artificial neural networks and human brain data processing patterns.
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.