Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911780427530240 |
|---|---|
| author | Zou, Wenxuan Huang, Haiping |
| author_facet | Zou, Wenxuan Huang, Haiping |
| contents | 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 physics. Here, we give a pedagogical introduction of this method in a particular example of random neural networks, where neurons are randomly and fully connected by correlated synapses and therefore the network exhibits rich emergent collective dynamics. We also review related past and recent important works applying this tool. In addition, a physically transparent and alternative method, namely the dynamical cavity method, is also introduced to derive exactly the same results. The numerical implementation of solving the integro-differential mean-field equations is also detailed, with an illustration of exploring the fluctuation dissipation theorem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_08459 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings Zou, Wenxuan Huang, Haiping Disordered Systems and Neural Networks Statistical Mechanics Machine Learning Neurons and Cognition 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 physics. Here, we give a pedagogical introduction of this method in a particular example of random neural networks, where neurons are randomly and fully connected by correlated synapses and therefore the network exhibits rich emergent collective dynamics. We also review related past and recent important works applying this tool. In addition, a physically transparent and alternative method, namely the dynamical cavity method, is also introduced to derive exactly the same results. The numerical implementation of solving the integro-differential mean-field equations is also detailed, with an illustration of exploring the fluctuation dissipation theorem. |
| title | Introduction to dynamical mean-field theory of randomly connected neural networks with bidirectionally correlated couplings |
| topic | Disordered Systems and Neural Networks Statistical Mechanics Machine Learning Neurons and Cognition |
| url | https://arxiv.org/abs/2305.08459 |