Dynamic neuron approach to deep neural networks: Decoupling neurons for renormalization group analysis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| 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 |