# Scaling up Echo-State Networks with multiple light scattering

arXiv: https://arxiv.org/abs/1609.05204 · HTML: https://mlsanity.com/paper/1609.05204/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2016.

## Built on by (most cited first, 4 of 4)

- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Wave-based extreme deep learning based on non-linear time-Floquet entanglement](https://mlsanity.com/paper/2107.08564/) (2021)
- [Asymptotic Stability in Reservoir Computing](https://mlsanity.com/paper/2206.03854/) (2022)
- [Improvement of image classification by multiple optical scattering](https://mlsanity.com/paper/2107.14051/) (2021)

## Abstract (arXiv)

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.