High-performance real-world optical computing trained by in situ gradient-based model-free optimization
arXiv:2307.11957 · doi:10.1109/TPAMI.2024.3466853
Abstract
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)
References in corpus (14)
- Deep Learning with Coherent Nanophotonic Circuits
- All-Optical Machine Learning Using Diffractive Deep Neural Networks
- Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
- Large-scale neuromorphic optoelectronic computing with a reconfigurable diffractive processing unit
- Training of photonic neural networks through in situ backpropagation
- Reinforcement Learning in a large scale photonic Recurrent Neural Network
- Image sensing with multilayer, nonlinear optical neural networks
- Delocalized Photonic Deep Learning on the Internet's Edge
- Large-Scale Optical Reservoir Computing for Spatiotemporal Chaotic Systems Prediction
- Scalable Optical Learning Operator
- All-optical image denoising using a diffractive visual processor
- Unidirectional Imaging using Deep Learning-Designed Materials
- Classification and reconstruction of spatially overlapping phase images using diffractive optical networks
- Broadband nonlinear modulation of incoherent light using a transparent optoelectronic neuron array