High-Performance Real-World Optical Computing Trained by in Situ Gradient-Based Model-Free Optimization
Uložené v:
| Názov: | High-Performance Real-World Optical Computing Trained by in Situ Gradient-Based Model-Free Optimization |
|---|---|
| Autori: | Guangyuan Zhao, Xin Shu, Renjie Zhou |
| Zdroj: | IEEE Transactions on Pattern Analysis and Machine Intelligence. 47:7194-7205 |
| Publication Status: | Preprint |
| Informácie o vydavateľovi: | Institute of Electrical and Electronics Engineers (IEEE), 2025. |
| Rok vydania: | 2025 |
| Predmety: | FOS: Computer and information sciences, Computer Science - Machine Learning, Emerging Technologies (cs.ET), Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Computer Science - Emerging Technologies, FOS: Physical sciences, Physics - Optics, Optics (physics.optics), Machine Learning (cs.LG) |
| Popis: | Optical computing systems provide high-speed and low-energy data processing but face deficiencies in computationally demanding training and simulation-to-reality gaps. We propose a gradient-based model-free optimization (G-MFO) method based on a Monte Carlo gradient estimation algorithm for computationally efficient in situ training of optical computing systems. This approach treats an optical computing system as a black box and back-propagates the loss directly to the optical computing weights' probability distributions, circumventing the need for a computationally heavy and biased system simulation. Our experiments on diffractive optical computing systems show that G-MFO outperforms hybrid training on the MNIST and FMNIST datasets. Furthermore, we demonstrate image-free and high-speed classification of cells from their marker-free phase maps. Our method's model-free and high-performance nature, combined with its low demand for computational resources, paves the way for accelerating the transition of optical computing from laboratory demonstrations to practical, real-world applications. The paper titled "High-performance real-world optical computing trained by in situ gradient-based model-free optimization" has been accepted at ICCP&TPAMI 2024. For more details, please visit the [project page](https://shuxin626.github.io/mfo_optical_computing/index.html) |
| Druh dokumentu: | Article |
| ISSN: | 1939-3539 0162-8828 |
| DOI: | 10.1109/tpami.2024.3466853 |
| DOI: | 10.48550/arxiv.2307.11957 |
| Prístupová URL adresa: | https://pubmed.ncbi.nlm.nih.gov/39316490 http://arxiv.org/abs/2307.11957 |
| Rights: | CC BY |
| Prístupové číslo: | edsair.doi.dedup.....d6e5783ebb918dbe5ba6729133004acf |
| Databáza: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Optical computing systems provide high-speed and low-energy data processing but face deficiencies in computationally demanding training and simulation-to-reality gaps. We propose a gradient-based model-free optimization (G-MFO) method based on a Monte Carlo gradient estimation algorithm for computationally efficient in situ training of optical computing systems. This approach treats an optical computing system as a black box and back-propagates the loss directly to the optical computing weights' probability distributions, circumventing the need for a computationally heavy and biased system simulation. Our experiments on diffractive optical computing systems show that G-MFO outperforms hybrid training on the MNIST and FMNIST datasets. Furthermore, we demonstrate image-free and high-speed classification of cells from their marker-free phase maps. Our method's model-free and high-performance nature, combined with its low demand for computational resources, paves the way for accelerating the transition of optical computing from laboratory demonstrations to practical, real-world applications.<br />The paper titled "High-performance real-world optical computing trained by in situ gradient-based model-free optimization" has been accepted at ICCP&TPAMI 2024. For more details, please visit the [project page](https://shuxin626.github.io/mfo_optical_computing/index.html) |
|---|---|
| ISSN: | 19393539 01628828 |
| DOI: | 10.1109/tpami.2024.3466853 |