Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > NLO > 2023 > M4A > M4A.26

Implementing a deep neural network using a single nonlinear element and delayed feedback

André Röhm, Florian Stelzer, Tomoaki Niiyama, Raul Vicente, Ingo Fischer, Makoto Naruse, Serhiy Yanchuk, and Satoshi Sunada

Not Accessible

Your library or personal account may give you access

Abstract

Optically implemented neural networks promise faster speeds and lower costs. However, large size networks remain challenging. We derive how to emulate a deep neural network with just a single nonlinear element using delayed feedback signals.

© 2023 The Author(s)

PDF Article
More Like This
A Photonic Deep Neural Network Processor on a Single Chip with Optically Accelerated Training

Saumil Bandyopadhyay, Alexander Sludds, Stefan Krastanov, Ryan Hamerly, Nicholas Harris, Darius Bunandar, Matthew Streshinsky, Michael Hochberg, and Dirk Englund
SM2P.2 CLEO: Science and Innovations (CLEO:S&I) 2023

Photonic delay-based reservoir computers as deep neural network preprocessors

Ian Bauwens, Guy Van der Sande, Peter Bienstman, and Guy Verschaffelt
jsiii_p_8 European Quantum Electronics Conference (EQEC) 2023

Single Pixel Image Reconstruction Using Nonlinear Optics and Neural Networks

Santosh Kumar, Matthew Thomas, and Yuping Huang
JM7A.126 Frontiers in Optics (FiO) 2023

View More...
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use