Scaling up Echo-State Networks with multiple light scattering

Abstract

Echo-State Networks and Reservoir Computing have been studied for more than a decade. They provide a simpler yet powerful alternative to Recurrent Neural Networks, every internal weight is fixed and only the last linear layer is trained. They involve many multiplications by dense random matrices. Very large networks are difficult to obtain, as the complexity scales quadratically both in time and memory. Here, we present a novel optical implementation of Echo-State Networks using light-scattering media and a Digital Micromirror Device. As a proof of concept, binary networks have been successfully trained to predict the chaotic Mackey-Glass time series. This new method is fast, power efficient and easily scalable to very large networks.

References in corpus (2)

• Reference-less measurement of the transmission matrix of a highly scattering material using a DMD and phase retrieval techniques
• Random Projections through multiple optical scattering: Approximating kernels at the speed of light

Cited by in corpus (4)

• Optical Reservoir Computing using multiple light scattering for chaotic systems prediction
• A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning
• Wave-based extreme deep learning based on non-linear time-Floquet entanglement
• Kernel computations from large-scale random features obtained by Optical Processing Units