Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083012432> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3083012432 abstract "Reservoir computing is a machine learning paradigm in which a high-dimensional dynamical system, or emph{reservoir}, is used to approximate and perform predictions on time series data. Its simple training procedure allows for very large reservoirs that can provide powerful computational capabilities. The scale, speed and power-usage characteristics of reservoir computing could be enhanced by constructing reservoirs out of electronic circuits, but this requires a precise understanding of how such circuits process and store information. We analyze the feasibility and optimal design of such reservoirs by considering the equations of motion of circuits that include both linear elements (resistors, inductors, and capacitors) and nonlinear memory elements (called memristors). This complements previous studies, which have examined such systems through simulation and experiment. We provide analytic results regarding the fundamental feasibility of such reservoirs, and give a systematic characterization of their computational properties, examining the types of input-output relationships that may be approximated. This allows us to design reservoirs with optimal properties in terms of their ability to reconstruct a certain signal (or functions thereof). In particular, by introducing measures of the total linear and nonlinear computational capacities of the reservoir, we are able to design electronic circuits whose total computation capacity scales linearly with the system size. Comparison with conventional echo state reservoirs show that these electronic reservoirs can match or exceed their performance in a form that may be directly implemented in hardware." @default.
- W3083012432 created "2020-09-11" @default.
- W3083012432 creator A5011236474 @default.
- W3083012432 creator A5022314625 @default.
- W3083012432 creator A5034041314 @default.
- W3083012432 date "2020-08-31" @default.
- W3083012432 modified "2023-09-27" @default.
- W3083012432 title "The Computational Capacity of Memristor Reservoirs" @default.
- W3083012432 hasPublicationYear "2020" @default.
- W3083012432 type Work @default.
- W3083012432 sameAs 3083012432 @default.
- W3083012432 citedByCount "1" @default.
- W3083012432 countsByYear W30830124322021 @default.
- W3083012432 crossrefType "posted-content" @default.
- W3083012432 hasAuthorship W3083012432A5011236474 @default.
- W3083012432 hasAuthorship W3083012432A5022314625 @default.
- W3083012432 hasAuthorship W3083012432A5034041314 @default.
- W3083012432 hasConcept C111919701 @default.
- W3083012432 hasConcept C11413529 @default.
- W3083012432 hasConcept C119599485 @default.
- W3083012432 hasConcept C121332964 @default.
- W3083012432 hasConcept C127413603 @default.
- W3083012432 hasConcept C134146338 @default.
- W3083012432 hasConcept C135796866 @default.
- W3083012432 hasConcept C137488568 @default.
- W3083012432 hasConcept C138331895 @default.
- W3083012432 hasConcept C147168706 @default.
- W3083012432 hasConcept C150072547 @default.
- W3083012432 hasConcept C154945302 @default.
- W3083012432 hasConcept C158622935 @default.
- W3083012432 hasConcept C165801399 @default.
- W3083012432 hasConcept C24326235 @default.
- W3083012432 hasConcept C41008148 @default.
- W3083012432 hasConcept C45374587 @default.
- W3083012432 hasConcept C50644808 @default.
- W3083012432 hasConcept C52192207 @default.
- W3083012432 hasConcept C62520636 @default.
- W3083012432 hasConcept C98045186 @default.
- W3083012432 hasConceptScore W3083012432C111919701 @default.
- W3083012432 hasConceptScore W3083012432C11413529 @default.
- W3083012432 hasConceptScore W3083012432C119599485 @default.
- W3083012432 hasConceptScore W3083012432C121332964 @default.
- W3083012432 hasConceptScore W3083012432C127413603 @default.
- W3083012432 hasConceptScore W3083012432C134146338 @default.
- W3083012432 hasConceptScore W3083012432C135796866 @default.
- W3083012432 hasConceptScore W3083012432C137488568 @default.
- W3083012432 hasConceptScore W3083012432C138331895 @default.
- W3083012432 hasConceptScore W3083012432C147168706 @default.
- W3083012432 hasConceptScore W3083012432C150072547 @default.
- W3083012432 hasConceptScore W3083012432C154945302 @default.
- W3083012432 hasConceptScore W3083012432C158622935 @default.
- W3083012432 hasConceptScore W3083012432C165801399 @default.
- W3083012432 hasConceptScore W3083012432C24326235 @default.
- W3083012432 hasConceptScore W3083012432C41008148 @default.
- W3083012432 hasConceptScore W3083012432C45374587 @default.
- W3083012432 hasConceptScore W3083012432C50644808 @default.
- W3083012432 hasConceptScore W3083012432C52192207 @default.
- W3083012432 hasConceptScore W3083012432C62520636 @default.
- W3083012432 hasConceptScore W3083012432C98045186 @default.
- W3083012432 hasLocation W30830124321 @default.
- W3083012432 hasOpenAccess W3083012432 @default.
- W3083012432 hasPrimaryLocation W30830124321 @default.
- W3083012432 hasRelatedWork W1578408466 @default.
- W3083012432 hasRelatedWork W2038849584 @default.
- W3083012432 hasRelatedWork W2065690384 @default.
- W3083012432 hasRelatedWork W2168723756 @default.
- W3083012432 hasRelatedWork W2210385882 @default.
- W3083012432 hasRelatedWork W2373820246 @default.
- W3083012432 hasRelatedWork W2734399270 @default.
- W3083012432 hasRelatedWork W2735356255 @default.
- W3083012432 hasRelatedWork W2788108519 @default.
- W3083012432 hasRelatedWork W2951279548 @default.
- W3083012432 hasRelatedWork W2982420760 @default.
- W3083012432 hasRelatedWork W3033510592 @default.
- W3083012432 hasRelatedWork W3083368431 @default.
- W3083012432 hasRelatedWork W3100729098 @default.
- W3083012432 hasRelatedWork W3102502580 @default.
- W3083012432 hasRelatedWork W3106539486 @default.
- W3083012432 hasRelatedWork W3125648070 @default.
- W3083012432 hasRelatedWork W3130984032 @default.
- W3083012432 hasRelatedWork W3198294736 @default.
- W3083012432 isParatext "false" @default.
- W3083012432 isRetracted "false" @default.
- W3083012432 magId "3083012432" @default.
- W3083012432 workType "article" @default.