BROWSE
Detail
Journal Article
Optical convolutional neural network with the hybrid training method
- Authors
- Jinhwa Gene, Suntak Park, Hyung Cheol Shin, Jong Moo Sohn
- Issue Date
- 2026-01
- Citation
- Neurocomputing, v.663, pp.1-8
- ISSN
- 0925-2312
- Publisher
- Elsevier
- Language
- English
- Type
- Journal Article
- Abstract
- Convolutional neural networks trained on electronic digital computers face deteriorated performance when inference is done with analog optical computing systems due to inherent analog noise. To reduce the impact of analog noise in an optical convolutional neural network, a hybrid training method is employed, using an optical convolution processor for forward propagation and an electronic digital computer for back-propagation. The inference accuracies of the network trained using this hybrid method on MNIST, Fashion-MNIST, and CIFAR-10 datasets were comparable to the results achieved by a network trained on an electronic digital computer, unaffected by analog computation errors.
- KSP Keywords
- Analog computation, Analog optical computing, Back-propagation, CIFAR-10, Computation errors, Convolution neural network(CNN), Digital computer, Forward Propagation, Hybrid training, computing systems, hybrid method
This work is distributed under the term of Creative Commons License (CCL)
(CC BY NC)
(CC BY NC)
