TRON: Trainable, architecture-reconfigurable random optical neural networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911613760569344 |
|---|---|
| author | Wang, Ziao Xia, Fei Wright, Logan G. Onodera, Tatsuhiro Stein, Martin Hu, Jianqi McMahon, Peter L. Gigan, Sylvain |
| author_facet | Wang, Ziao Xia, Fei Wright, Logan G. Onodera, Tatsuhiro Stein, Martin Hu, Jianqi McMahon, Peter L. Gigan, Sylvain |
| contents | Deep learning has triggered explosive growth in the demand for specialized hardware processors, thus motivating the development of scalable and reconfigurable computing substrates. Optical processors offer a fundamentally different computing paradigm, combining massive parallelism and ultrahigh bandwidth with the potential for substantial energy savings. However, progress has been constrained by the absence of scalable and reconfigurable architectures that can implement a broad class of network architectures. Here, we introduce TRON, a scalable and trainable optoelectronic deep optical neural network that exploits a multi-scattering medium and a DMD as a learnable, high-dimensional dense optical matrix multiplier, processing with fixed and tunable optical operations. We perform in-situ optimization of the optical parameters involved in the scattering process, together with automated neural architecture search (NAS) and optimization directly on optics. The experimental results demonstrate that in-situ NAS is essential to discover architectures that adapt to both the task and hardware constraints, establishing a viable path towards large-scale optical processors for next-generation machine learning and data-intensive computing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16228 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TRON: Trainable, architecture-reconfigurable random optical neural networks Wang, Ziao Xia, Fei Wright, Logan G. Onodera, Tatsuhiro Stein, Martin Hu, Jianqi McMahon, Peter L. Gigan, Sylvain Optics Applied Physics Deep learning has triggered explosive growth in the demand for specialized hardware processors, thus motivating the development of scalable and reconfigurable computing substrates. Optical processors offer a fundamentally different computing paradigm, combining massive parallelism and ultrahigh bandwidth with the potential for substantial energy savings. However, progress has been constrained by the absence of scalable and reconfigurable architectures that can implement a broad class of network architectures. Here, we introduce TRON, a scalable and trainable optoelectronic deep optical neural network that exploits a multi-scattering medium and a DMD as a learnable, high-dimensional dense optical matrix multiplier, processing with fixed and tunable optical operations. We perform in-situ optimization of the optical parameters involved in the scattering process, together with automated neural architecture search (NAS) and optimization directly on optics. The experimental results demonstrate that in-situ NAS is essential to discover architectures that adapt to both the task and hardware constraints, establishing a viable path towards large-scale optical processors for next-generation machine learning and data-intensive computing. |
| title | TRON: Trainable, architecture-reconfigurable random optical neural networks |
| topic | Optics Applied Physics |
| url | https://arxiv.org/abs/2604.16228 |