Physical Neural Networks with Self-Learning Capabilities
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929455227731968 |
|---|---|
| author | Yu, Weichao Guo, Hangwen Xiao, Jiang Shen, Jian |
| author_facet | Yu, Weichao Guo, Hangwen Xiao, Jiang Shen, Jian |
| contents | Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials. These networks harness the distinctive characteristics of physical systems to carry out computations effectively, potentially surpassing the constraints of conventional digital neural networks. A recent advancement known as ``physical self-learning'' aims to achieve learning through intrinsic physical processes rather than relying on external computations. This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems. Prevailing learning strategies are discussed that contribute to the realization of physical self-learning. Despite challenges in understanding fundamental mechanism of learning, this work highlights the progress towards constructing intelligent hardware from the ground up, incorporating embedded self-organizing and self-adaptive dynamics in physical systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05464 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Physical Neural Networks with Self-Learning Capabilities Yu, Weichao Guo, Hangwen Xiao, Jiang Shen, Jian Applied Physics Disordered Systems and Neural Networks Physical neural networks are artificial neural networks that mimic synapses and neurons using physical systems or materials. These networks harness the distinctive characteristics of physical systems to carry out computations effectively, potentially surpassing the constraints of conventional digital neural networks. A recent advancement known as ``physical self-learning'' aims to achieve learning through intrinsic physical processes rather than relying on external computations. This article offers a comprehensive review of the progress made in implementing physical self-learning across various physical systems. Prevailing learning strategies are discussed that contribute to the realization of physical self-learning. Despite challenges in understanding fundamental mechanism of learning, this work highlights the progress towards constructing intelligent hardware from the ground up, incorporating embedded self-organizing and self-adaptive dynamics in physical systems. |
| title | Physical Neural Networks with Self-Learning Capabilities |
| topic | Applied Physics Disordered Systems and Neural Networks |
| url | https://arxiv.org/abs/2408.05464 |