NN-QFT

The Principle of Deep Learning Theory

There is a theory what I need.

0. Initialization

1. Pretraining

2. Neural Networks

3. Effective Theory of Deep Linear Networks at Initialization

4. RG Flow of Preactivations

5. Effective Theory of Preactivations at Initialization

6. Bayesian Learning

7. Gradient-Based Learning

8. RG Flow of the Neural Tangent Kernel

9. Effective Theory of the NTK at Initialization

10. Kernel Learning

11. Representation Learning

$\infty$. The End of Training

$\epsilon$. Epilogue: Model Complexity from the Macroscopic Perspective

A. Information in Deep Learning

B. Resudyal Learning

Use

This is one part of ULA.

NN-QFT is combination of QFT and Optimization.

Reference

The Principles of Deep Learning Theory