Photonic pattern reconstruction enabled by on-chip online learning and inference

Recent investigations in neuromorphic photonics exploit optical device physics for neuron models, and optical interconnects for distributed, parallel, and analog processing. Integrated solutions enabled by silicon photonics enable high-bandwidth, low-latency and low switching energy, making it a pro...

Full description

Saved in:
Bibliographic Details
Published in:JPhys photonics 2021-04, Vol.3 (2), p.24006
Main Authors: Marquez, Bicky A, Guo, Zhimu, Morison, Hugh, Shekhar, Sudip, Chrostowski, Lukas, Prucnal, Paul, Shastri, Bhavin J
Format: Article
Language:English
Subjects:
Accelerators
Artificial intelligence
Machine learning
Network latency
Online instruction
Optical interconnects
Photonics
Recurrent neural networks
Silicon
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent investigations in neuromorphic photonics exploit optical device physics for neuron models, and optical interconnects for distributed, parallel, and analog processing. Integrated solutions enabled by silicon photonics enable high-bandwidth, low-latency and low switching energy, making it a promising candidate for special-purpose artificial intelligence hardware accelerators. Here, we experimentally demonstrate a silicon photonic chip that can perform training and testing of a Hopfield network, i.e. recurrent neural network, via vector dot products. We demonstrate that after online training, our trained Hopfield network can successfully reconstruct corrupted input patterns.
ISSN:2515-7647
2515-7647
DOI:10.1088/2515-7647/abe3d9