Photonic extreme learning machine based on frequency multiplexing

The optical domain is a promising field for the 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. (C) 2021 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Automated summary

The optical domain is a promising field for implementing neural networks due to its speed and parallelism. Extreme Learning Machines (ELMs) are feed-forward neural networks where only output weights are trained, while internal connections remain untrained. Experimental results show that photonic ELM performs well in classification tasks and nonlinear channel equalization tasks.