Journal article icon

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


Access Document


Files:
Publisher copy:
10.1364/PRJ.411104

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Sub department:
Atomic & Laser Physics
Role:
Author
ORCID:
0000-0001-6241-3028
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Physics
Sub department:
Atomic & Laser Physics
Oxford college:
Keble College
Role:
Author
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
Language:
English
Keywords:
Pubs id:
1081067
Local pid:
pubs:1081067
Deposit date:
2021-03-19

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP