Presentation
4 October 2023 Energy-based neural network models with coherent laser networks
Mohammad-Ali Miri, Kevin Zelaya
Author Affiliations +
Abstract
We propose utilizing coherently coupled laser networks for neural computing. The proposed scheme is built on harnessing the collective behavior of laser networks for storing phase patterns as stable fixed points of the governing dynamical equations and retrieving such patterns through proper excitation conditions, thus exhibiting an associative memory property. We further show that limitations on the number of images can be overcome by using nonreciprocal coupling between lasers, thus allowing for utilizing the large storage capacity inherent to the laser network. This work opens new possibilities for neural computation with coherent laser networks as a novel physical analog processor.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mohammad-Ali Miri and Kevin Zelaya "Energy-based neural network models with coherent laser networks", Proc. SPIE PC12647, Active Photonic Platforms (APP) 2023, PC126470L (4 October 2023); https://doi.org/10.1117/12.2679117
Advertisement
Advertisement
KEYWORDS
Physical coherence

Neural networks

Analog electronics

Content addressable memory

RELATED CONTENT

Fault tolerance of opto-electronic neural networks
Proceedings of SPIE (December 01 1991)
Recent research on optical neural networks in Japan
Proceedings of SPIE (November 01 1991)
Neural networks for matched filter selection and synthesis
Proceedings of SPIE (September 16 1992)
Optimization of VQ architectures
Proceedings of SPIE (October 20 1993)

Back to Top