Nonlinear unitary circuits for photonic neural networks
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917545228894208 |
|---|---|
| author | Yu, Sunkyu Piao, Xianji Park, Namkyoo |
| author_facet | Yu, Sunkyu Piao, Xianji Park, Namkyoo |
| contents | Photonics has unlocked the potential for energy-efficient acceleration of deep learning. Most approaches toward photonic deep learning have diligently reproduced traditional deep learning architectures using photonic platforms, separately implementing linear-optical matrix calculations and nonlinear activations via electro-optical conversion, optical nonlinearities, and signal-encoded materials. Here we propose a concept of nonlinear unitary photonic circuits to achieve the integration of linear and nonlinear expressivity essential for deep neural networks. We devise a building block for two-dimensional nonlinear unitary operations, featuring norm-preserving mappings with nonconservative inner products, which enables the construction of high-dimensional nonlinear unitary circuits. Using deep nonlinear unitary circuits, we demonstrate exponential growth in trajectory length and near-complete coverage of the output space, both of which are essential for deep learning. Along with neuroevolutionary learning examples for the regression of a nonconvex function, our results pave the way to photonic neural networks with highly expressive inference and stable training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04112 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Nonlinear unitary circuits for photonic neural networks Yu, Sunkyu Piao, Xianji Park, Namkyoo Optics Photonics has unlocked the potential for energy-efficient acceleration of deep learning. Most approaches toward photonic deep learning have diligently reproduced traditional deep learning architectures using photonic platforms, separately implementing linear-optical matrix calculations and nonlinear activations via electro-optical conversion, optical nonlinearities, and signal-encoded materials. Here we propose a concept of nonlinear unitary photonic circuits to achieve the integration of linear and nonlinear expressivity essential for deep neural networks. We devise a building block for two-dimensional nonlinear unitary operations, featuring norm-preserving mappings with nonconservative inner products, which enables the construction of high-dimensional nonlinear unitary circuits. Using deep nonlinear unitary circuits, we demonstrate exponential growth in trajectory length and near-complete coverage of the output space, both of which are essential for deep learning. Along with neuroevolutionary learning examples for the regression of a nonconvex function, our results pave the way to photonic neural networks with highly expressive inference and stable training. |
| title | Nonlinear unitary circuits for photonic neural networks |
| topic | Optics |
| url | https://arxiv.org/abs/2412.04112 |