Optoelectronic reservoir computing. - National Genomics Data Center (CNCB-NGDC)

Advanced Search

Optoelectronic reservoir computing.

Y Paquot, F Duport, A Smerieri, J Dambre, B Schrauwen, M Haelterman, S Massar

Author Information

PMID: 22371825 DOI: 10.1038/srep00287

Reservoir computing is a recently introduced, highly efficient bio-inspired approach for processing time dependent data. The basic scheme of reservoir computing consists of a non linear recurrent dynamical system coupled to a single input layer and a single output layer. Within these constraints many implementations are possible. Here we report an optoelectronic implementation of reservoir computing based on a recently proposed architecture consisting of a single non linear node and a delay line. Our implementation is sufficiently fast for real time information processing. We illustrate its performance on tasks of practical importance such as nonlinear channel equalization and speech recognition, and obtain results comparable to state of the art digital implementations.

Phys Rev Lett. 2005 Jul 22;95(4):043903 [PMID: 16090809]
Neural Netw. 2007 Apr;20(3):391-403 [PMID: 17517492]
Neural Comput. 2002 Nov;14(11):2531-60 [PMID: 12433288]
IEEE Trans Neural Netw. 2000;11(3):697-709 [PMID: 18249797]
Opt Express. 2012 Jan 30;20(3):3241-9 [PMID: 22330562]
Phys Rev Lett. 2005 Nov 11;95(20):203903 [PMID: 16384058]
Science. 2004 Apr 2;304(5667):78-80 [PMID: 15064413]
Phys Rev E Stat Nonlin Soft Matter Phys. 2009 Feb;79(2 Pt 2):026208 [PMID: 19391821]
Opt Express. 2008 Jul 21;16(15):11182-92 [PMID: 18648434]
Nat Commun. 2011 Sep 13;2:468 [PMID: 21915110]
IEEE Trans Neural Netw. 2011 Jan;22(1):131-44 [PMID: 21075721]
Neural Netw. 2007 Apr;20(3):335-52 [PMID: 17517495]

Journal Article

Optoelectronic reservoir computing: tackling noise-induced performance degradation.Reservoir computing system with double optoelectronic feedback loops.Photonic reinforcement learning based on optoelectronic reservoir computing.IGZO/PVP Composite Nanofiber Neuromorphic Transistors with Optoelectronic Synapse Emulation and Reservoir Computing.Human recognition with the optoelectronic reservoir-computing-based micro-Doppler radar signal processing.A Multiple-Input Multiple-Output Reservoir Computing System Subject to Optoelectronic Feedbacks and Mutual Coupling.Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing.Efficient optoelectronic reservoir computing with three-route input based on optical delay lines.Ultralow-power optoelectronic synaptic transistors based on polyzwitterion dielectrics for in-sensor reservoir computing.Organic Polymer-Based Photodiodes for Optoelectronic Reservoir Computing with Time-Based Coding.

Digital Modeling on Large Kernel Metamaterial Neural Network.Application of the deep learning for the prediction of rainfall in Southern Taiwan.Exploiting Pull-In/Pull-Out Hysteresis in Electrostatic MEMS Sensor Networks to Realize a Novel Sensing Continuous-Time Recurrent Neural Network.Neuromorphic Computing through Time-Multiplexing with a Spin-Torque Nano-Oscillator.All-Optical Implementation of the Ant Colony Optimization Algorithm.Simulating self-learning in photorefractive optical reservoir computers.Constructing optimized binary masks for reservoir computing with delay systems.Parallel photonic information processing at gigabyte per second data rates using transient states.Morphological Computation: Nothing but Physical Computation.Computing with networks of nonlinear mechanical oscillators.

See all "Cited by" articles