Information processing using a single dynamical node as complex system
Autor: | Ingo Fischer, G. Van der Sande, Claudio R. Mirasso, Lennert Appeltant, Serge Massar, Joni Dambre, Miguel C. Soriano, Benjamin Schrauwen, Jan Danckaert |
---|---|
Přispěvatelé: | Applied Physics, Physics, Applied Physics and Photonics |
Jazyk: | angličtina |
Rok vydání: | 2011 |
Předmět: |
Dynamical systems theory
Computation Complex system General Physics and Astronomy 02 engineering and technology Bioinformatics 01 natural sciences General Biochemistry Genetics and Molecular Biology Article nonlinear dynamics 0103 physical sciences 010306 general physics Delay Multidisciplinary applied physics Node (networking) Reservoir computing Information processing General Chemistry Complex network 021001 nanoscience & nanotechnology Computer engineering Benchmark (computing) 0210 nano-technology physics Neuroscience |
Zdroj: | Vrije Universiteit Brussel Nature Communications |
Popis: | Novel methods for information processing are highly desired in our information-driven society. Inspired by the brain's ability to process information, the recently introduced paradigm known as 'reservoir computing' shows that complex networks can efficiently perform computation. Here we introduce a novel architecture that reduces the usually required large number of elements to a single nonlinear node with delayed feedback. Through an electronic implementation, we experimentally and numerically demonstrate excellent performance in a speech recognition benchmark. Complementary numerical studies also show excellent performance for a time series prediction benchmark. These results prove that delay-dynamical systems, even in their simplest manifestation, can perform efficient information processing. This finding paves the way to feasible and resource-efficient technological implementations of reservoir computing. The paradigm of reservoir computing shows that, like the human brain, complex networks can perform efficient information processing. Here, a simple delay dynamical system is demonstrated that can efficiently perform computations capable of replacing a complex network in reservoir computing. |
Databáze: | OpenAIRE |
Externí odkaz: |