Journal article
Backpropagation through nonlinear units for the all-optical training of neural networks
- Abstract:
-
We propose a practical scheme for end-to-end optical backpropagation in neural networks. Using saturable absorption for the nonlinear units, we find that the backward-propagating gradients required to train the network can be approximated in a surprisingly simple pump-probe scheme that requires only simple passive optical elements. Simulations show that, with readily obtainable optical depths, our approach can achieve equivalent performance to state-of-the-art computational networks on image ...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Optical Society of America Publisher's website
- Journal:
- Photonics Research Journal website
- Volume:
- 9
- Issue:
- 3
- Pages:
- B71-B80
- Publication date:
- 2021-03-01
- Acceptance date:
- 2021-01-11
- DOI:
- EISSN:
-
2327-9125
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
1081067
- Local pid:
- pubs:1081067
- Deposit date:
- 2021-03-19
Terms of use
- Copyright holder:
- Chinese Laser Press
- Copyright date:
- 2021
- Rights statement:
- © 2021 Chinese Laser Press.
- Notes:
- This is the accepted manuscript version of the article. The final version is available online from Chinese Laser Press at: https://doi.org/10.1364/PRJ.411104
If you are the owner of this record, you can report an update to it here: Report update to this record