Opening the black box of deep learning

TL;DR

This paper explores the internal mechanisms of deep learning by viewing neural networks as physical systems, applying physics principles to explain core processes and limitations, and proposing a physics-based theoretical foundation for future development.

Contribution

It introduces a physics-based perspective on deep learning, providing novel explanations for neural network operations and limitations using principles from quantum mechanics and statistical physics.

Findings

Calculation methods for convolution, pooling, and normalization derived from physics

Explanation of why deep learning models must be deep

Insights into why CNNs do not need layer-by-layer training

Abstract

The great success of deep learning shows that its technology contains profound truth, and understanding its internal mechanism not only has important implications for the development of its technology and effective application in various fields, but also provides meaningful insights into the understanding of human brain mechanism. At present, most of the theoretical research on deep learning is based on mathematics. This dissertation proposes that the neural network of deep learning is a physical system, examines deep learning from three different perspectives: microscopic, macroscopic, and physical world views, answers multiple theoretical puzzles in deep learning by using physics principles. For example, from the perspective of quantum mechanics and statistical physics, this dissertation presents the calculation methods for convolution calculation, pooling, normalization, and Restricted Boltzmann Machine, as well as the selection of cost functions, explains why deep learning must be deep, what characteristics are learned in deep learning, why Convolutional Neural Networks do not have to be trained layer by layer, and the limitations of deep learning, etc., and proposes the theoretical direction and basis for the further development of deep learning now and in the future. The brilliance of physics flashes in deep learning, we try to establish the deep learning technology based on the scientific theory of physics.