Presentation + Paper
2 September 2021 Frequency multiplexed optical extreme learning machine
Alessandro Lupo, Lorenz Butschek, Serge Massar
Author Affiliations +
Abstract
We propose an optical implementation of an Extreme Learning Machine (ELM) inspired by frequency-multiplexing techniques previously employed for Reservoir Computing. The input layer of the ELM is encoded in the lines of a frequency comb and the hidden layer is generated by making comb lines interfere. Multiplication by output weights can be performed optically. This approach combines the potential high-speed, low-power and paral- lelization advantages of Optical Neural Networks with the cheap training (both in terms of speed and power) of ELMs, which do not require slow gradient descent and error backpropagation algorithms. We present preliminary experimental results compared with simulations.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Alessandro Lupo, Lorenz Butschek, and Serge Massar "Frequency multiplexed optical extreme learning machine", Proc. SPIE 11804, Emerging Topics in Artificial Intelligence (ETAI) 2021, 118041N (2 September 2021); https://doi.org/10.1117/12.2593955
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Optical filters

Phase modulation

Photodiodes

Signal attenuation

Frequency combs

Network architectures

Neural networks

Back to Top