All-Optical Deep Learning with Quantum Nonlinearity
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909981218963456 |
|---|---|
| author | Zhou, Qingyi Kim, Jungmin Tao, Yutian Huang, Guoming Zhou, Ming Shao, Zewei Yu, Zongfu |
| author_facet | Zhou, Qingyi Kim, Jungmin Tao, Yutian Huang, Guoming Zhou, Ming Shao, Zewei Yu, Zongfu |
| contents | The rapid scaling of deep neural networks comes at the cost of unsustainable power consumption. While optical neural networks offer an alternative, their capabilities remain constrained by the lack of efficient optical nonlinearities. To address this, we propose an all-optical deep learning architecture by embedding quantum emitters in inverse-designed nanophotonic structures. Due to their saturability, quantum emitters exhibit exceptionally strong nonlinearity compared with conventional materials. Using physics-aware training, we demonstrate that the proposed architecture can solve complex tasks, including nonlinear classification and reinforcement learning, which have not been realized in all-optical neural networks. To enable fair comparison across different platforms, we introduce a framework that quantitatively links nonlinearity to a network's expressive power. Analysis shows that our quantum activation, operating below nW/μm^2 intensity, reduces the power budget by seven orders of magnitude. System-level estimates show that the optical power required for large language models scales sublinearly with model size, enabling watt-level operation. Our results indicate that quantum nanophotonics provides a route toward sustainable AI inference. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_01690 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | All-Optical Deep Learning with Quantum Nonlinearity Zhou, Qingyi Kim, Jungmin Tao, Yutian Huang, Guoming Zhou, Ming Shao, Zewei Yu, Zongfu Optics Applied Physics Computational Physics The rapid scaling of deep neural networks comes at the cost of unsustainable power consumption. While optical neural networks offer an alternative, their capabilities remain constrained by the lack of efficient optical nonlinearities. To address this, we propose an all-optical deep learning architecture by embedding quantum emitters in inverse-designed nanophotonic structures. Due to their saturability, quantum emitters exhibit exceptionally strong nonlinearity compared with conventional materials. Using physics-aware training, we demonstrate that the proposed architecture can solve complex tasks, including nonlinear classification and reinforcement learning, which have not been realized in all-optical neural networks. To enable fair comparison across different platforms, we introduce a framework that quantitatively links nonlinearity to a network's expressive power. Analysis shows that our quantum activation, operating below nW/μm^2 intensity, reduces the power budget by seven orders of magnitude. System-level estimates show that the optical power required for large language models scales sublinearly with model size, enabling watt-level operation. Our results indicate that quantum nanophotonics provides a route toward sustainable AI inference. |
| title | All-Optical Deep Learning with Quantum Nonlinearity |
| topic | Optics Applied Physics Computational Physics |
| url | https://arxiv.org/abs/2601.01690 |