Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913469249355776 |
|---|---|
| author | Ahmadnejad, Amirreza Koohi, Somayyeh |
| author_facet | Ahmadnejad, Amirreza Koohi, Somayyeh |
| contents | This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method that avoids specific nonlinear activation functions by modulating and re-entering error with random noise. Additionally, we propose a new way to implement convolutional neural networks using simple neural networks in integrated optical systems. Theoretical foundations and numerical results demonstrate significant improvements in training speed, energy efficiency, and scalability, advancing the potential of optical computing for complex data tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08337 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation Ahmadnejad, Amirreza Koohi, Somayyeh Machine Learning Optics This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method that avoids specific nonlinear activation functions by modulating and re-entering error with random noise. Additionally, we propose a new way to implement convolutional neural networks using simple neural networks in integrated optical systems. Theoretical foundations and numerical results demonstrate significant improvements in training speed, energy efficiency, and scalability, advancing the potential of optical computing for complex data tasks. |
| title | Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation |
| topic | Machine Learning Optics |
| url | https://arxiv.org/abs/2408.08337 |