Reservoir computing with a single time-delay autonomous Boolean node
Autor: | Daniel J. Gauthier, Ingo Fischer, Miguel C. Soriano, David P. Rosin, Nicholas D. Haynes |
---|---|
Přispěvatelé: | Govern de les Illes Balears, Ministerio de Economía y Competitividad (España), US Army Research Laboratory, National Science Foundation (US) |
Rok vydání: | 2015 |
Předmět: |
FOS: Computer and information sciences
Time Factors Operations research Computer science Chaotic Physical system MathematicsofComputing_NUMERICALANALYSIS FOS: Physical sciences Computer Science - Emerging Technologies 01 natural sciences 010305 fluids & plasmas Pattern Recognition Automated Consistency (database systems) 0103 physical sciences Transient (computer programming) 010306 general physics Operating point Computers Reservoir computing Nonlinear Sciences - Adaptation and Self-Organizing Systems Nonlinear system Emerging Technologies (cs.ET) Nonlinear Dynamics Linear Models Node (circuits) Algorithm Adaptation and Self-Organizing Systems (nlin.AO) |
Zdroj: | Digital.CSIC. Repositorio Institucional del CSIC instname |
Popis: | © 2015 American Physical Society. We demonstrate reservoir computing with a physical system using a single autonomous Boolean logic element with time-delay feedback. The system generates a chaotic transient with a window of consistency lasting between 30 and 300 ns, which we show is sufficient for reservoir computing. We then characterize the dependence of computational performance on system parameters to find the best operating point of the reservoir. When the best parameters are chosen, the reservoir is able to classify short input patterns with performance that decreases over time. In particular, we show that four distinct input patterns can be classified for 70 ns, even though the inputs are only provided to the reservoir for 7.5 ns. N.D.H. and D.J.G. gratefully acknowledge financial support from the U.S. Army Research Office through Grant No. W911NF-12-1-0099. N.D.H. also acknowledges the U.S. National Science Foundation for support through Grant No. DGE-1068871. M.C.S. and I.F. acknowledge support from Ministerio de Economía y Competitividad (Spain) under Project No. TEC2012-36335 (TRIPHOP) and Govern de les Illes Balears via the program Grups Competitius. |
Databáze: | OpenAIRE |
Externí odkaz: |