Fiber-based diffractive deep neural network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909497454231552 |
|---|---|
| author | Kesgin, Bahadır Utku Yüce, Firdevs Teğin, Uğur |
| author_facet | Kesgin, Bahadır Utku Yüce, Firdevs Teğin, Uğur |
| contents | Optical computing has reemerged as a promising alternative computing paradigm for providing energy-efficient information processing in the age of artificial intelligence. Among various photonic neural network platforms, diffractive optical processing systems in free space proved high-performance computing with high parallelism. Here, we report fiber-based diffractive deep neural networks by optimizing the linear coupling of the waveguide modes. Our approach demonstrated high performance in various machine learning tasks such as biomedical disease, fashion, and geospatial classification with a simple readout layer and all-optically. Operating on linear optics, our architecture performs on par with neural networks even in complex datasets where the data cannot be separated using linear operations. These results will enable efficient and scalable diffractive information processing with waveguides for real-life computing, telecommunications, and imaging applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11885 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fiber-based diffractive deep neural network Kesgin, Bahadır Utku Yüce, Firdevs Teğin, Uğur Optics Optical computing has reemerged as a promising alternative computing paradigm for providing energy-efficient information processing in the age of artificial intelligence. Among various photonic neural network platforms, diffractive optical processing systems in free space proved high-performance computing with high parallelism. Here, we report fiber-based diffractive deep neural networks by optimizing the linear coupling of the waveguide modes. Our approach demonstrated high performance in various machine learning tasks such as biomedical disease, fashion, and geospatial classification with a simple readout layer and all-optically. Operating on linear optics, our architecture performs on par with neural networks even in complex datasets where the data cannot be separated using linear operations. These results will enable efficient and scalable diffractive information processing with waveguides for real-life computing, telecommunications, and imaging applications. |
| title | Fiber-based diffractive deep neural network |
| topic | Optics |
| url | https://arxiv.org/abs/2502.11885 |