Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lee, Donghee, Lee, Hye-Sung, Yi, Jaeok
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915368136605696
author Lee, Donghee
Lee, Hye-Sung
Yi, Jaeok
author_facet Lee, Donghee
Lee, Hye-Sung
Yi, Jaeok
contents Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of deep learning. Similarly to how a power strip helps untangle and organize complex cable connections, this approach treats neurons as additional degrees of freedom in interactions, simplifying the structure and enhancing the intuitive understanding of interactions within deep neural networks. Furthermore, it reveals the translational symmetry of deep neural networks, which simplifies the application of the renormalization group transformation-a method that effectively analyzes the scaling behavior of the system. By utilizing translational symmetry and renormalization group transformations, we can analyze critical phenomena. This approach may open new avenues for studying deep neural networks using statistical physics.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00396
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis
Lee, Donghee
Lee, Hye-Sung
Yi, Jaeok
Statistical Mechanics
Disordered Systems and Neural Networks
Machine Learning
Deep neural network architectures often consist of repetitive structural elements. We introduce an approach that reveals these patterns and can be broadly applied to the study of deep learning. Similarly to how a power strip helps untangle and organize complex cable connections, this approach treats neurons as additional degrees of freedom in interactions, simplifying the structure and enhancing the intuitive understanding of interactions within deep neural networks. Furthermore, it reveals the translational symmetry of deep neural networks, which simplifies the application of the renormalization group transformation-a method that effectively analyzes the scaling behavior of the system. By utilizing translational symmetry and renormalization group transformations, we can analyze critical phenomena. This approach may open new avenues for studying deep neural networks using statistical physics.
title Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis
topic Statistical Mechanics
Disordered Systems and Neural Networks
Machine Learning
url https://arxiv.org/abs/2410.00396