paper-with-me

Papers

Scaling up Echo-State Networks with multiple light scattering

2016-09-15 · Jonathan Dong, Sylvain Gigan, Florent Krzakala, Gilles Wainrib

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.

📄 PDF Abstract BibTeX arXiv:1609.05204

Code (0)

등록된 구현이 없습니다.

Tasks

Time SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

Nonlinear Processing with Linear Optics

2023-07-17 · Mustafa Yıldırım, Niyazi Ulas Dinc, Ilker Oguz, Demetri Psaltis 외

Deep neural networks have achieved remarkable breakthroughs by leveraging multiple layers of data processing to extract hidden representations, albeit at the cost of large electronic computing power. To enhance energy ef…

ISAR Imaging Analysis of a Hypersonic Vehicle Covered With Plasma Sheath

2021-10-09 · journal 2021 10 · Bian Zheng

In this article, a hypersonic target electromagnetic (EM) scattering echo model combined with the inhomogeneous zonal medium model (IZMM) and the classical scattering center model (SCM) is proposed with a distributed …

Motion Compensation

Optical diffraction neural networks assisted computational ghost imaging through dynamic scattering media

2025-11-28 · Yue-Gang Li, Ze Zheng, Jun-jie Wang, Ming He 외 arxiv

Ghost imaging leverages a single-pixel detector with no spatial resolution to acquire object echo intensity signals, which are correlated with illumination patterns to reconstruct an image. This architecture inherently m…

Quantitative processing of broadband data as implemented in a scientific splitbeam echosounder

2021-04-15 · Lars Nonboe Andersen, Dezhang Chu, Harald Heimvoll, Rolf Korneliussen 외

The use of quantitative broadband echosounders for biological studies and surveys offers considerable advantages over narrowband echosounders. These include improved spectral-based target identification and significantly…

Rigid-Motion Scattering for Texture Classification

2014-03-07 · Laurent SIfre, Stéphane Mallat

A rigid-motion scattering computes adaptive invariants along translations and rotations, with a deep convolutional network. Convolutions are calculated on the rigid-motion group, with wavelets defined on the translation …

ClassificationGeneral ClassificationTexture ClassificationTranslation