Scaling up Echo-State Networks with multiple light scattering
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Time SeriesTime Series AnalysisMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Nonlinear Processing with Linear Optics
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
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 CompensationOptical diffraction neural networks assisted computational ghost imaging through dynamic scattering media
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
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
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