Optoelectronic reservoir computing: tackling noise-induced performance degradation
- 2 January 2013
- journal article
- research article
- Published by Optica Publishing Group in Optics Express
- Vol. 21 (1) , 12-20
Abstract
We present improved strategies to perform photonic information processing using an optoelectronic oscillator with delayed feedback. In particular, we study, via numerical simulations and experiments, the influence of a finite signal-to-noise ratio on the computing performance. We illustrate that the performance degradation induced by noise can be compensated for via multi-level pre-processing masks.Keywords
This publication has 24 references indexed in Scilit:
- Information processing using a single dynamical node as complex systemNature Communications, 2011
- Parallel Reservoir Computing Using Optical AmplifiersIEEE Transactions on Neural Networks, 2011
- Why future supercomputing requires opticsNature Photonics, 2010
- Toward optical signal processing using Photonic Reservoir ComputingOptics Express, 2008
- Transient Dynamics for Neural ProcessingScience, 2008
- Optical Quantum ComputingScience, 2007
- An experimental unification of reservoir computing methodsNeural Networks, 2007
- On the computational power of circuits of spiking neuronsJournal of Computer and System Sciences, 2004
- Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless CommunicationScience, 2004
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002