Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
Dynamical mean-field theory is a powerful physics tool used to analyze the typical behavior of neural networks, where neurons can be recurrently connected, or multiple layers of neurons can be stacked. However, it is not easy for beginners to access the essence of this tool and the underlying physic...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SciPost
2024-02-01
|
| Series: | SciPost Physics Lecture Notes |
| Online Access: | https://scipost.org/SciPostPhysLectNotes.79 |