Optica Open
arXiv.svg (5.58 kB)
Download file

Photonic Extreme Learning Machine based on frequency multiplexing

Download (5.58 kB)
posted on 2023-01-11, 23:15 authored by Alessandro Lupo, Lorenz Butschek, Serge Massar
The optical domain is a promising field for physical implementation of neural networks, due to the speed and parallelism of optics. Extreme Learning Machines (ELMs) are feed-forward neural networks in which only output weights are trained, while internal connections are randomly selected and left untrained. Here we report on a photonic ELM based on a frequency-multiplexed fiber setup. Multiplication by output weights can be performed either offline on a computer, or optically by a programmable spectral filter. We present both numerical simulations and experimental results on classification tasks and a nonlinear channel equalization task.



This arXiv metadata record was not reviewed or approved by, nor does it necessarily express or reflect the policies or opinions of, arXiv.

Usage metrics