Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366996581> ?p ?o ?g. }
- W4366996581 abstract "Reservoir computing, a recurrent neural network paradigm in which only the output layer is trained, has demonstrated remarkable performance on tasks such as prediction and control of nonlinear systems. Recently, it was demonstrated that adding time-shifts to the signals generated by a reservoir can provide large improvements in performance accuracy. In this work, we present a technique to choose the time-shifts by maximizing the rank of the reservoir matrix using a rank-revealing QR algorithm. This technique, which is not task dependent, does not require a model of the system, and therefore is directly applicable to analog hardware reservoir computers. We demonstrate our time-shift selection technique on two types of reservoir computer: one based on an opto-electronic oscillator and the traditional recurrent network with a $tanh$ activation function. We find that our technique provides improved accuracy over random time-shift selection in essentially all cases." @default.
- W4366996581 created "2023-04-27" @default.
- W4366996581 creator A5020186212 @default.
- W4366996581 creator A5034065247 @default.
- W4366996581 creator A5063085099 @default.
- W4366996581 date "2023-04-01" @default.
- W4366996581 modified "2023-10-14" @default.
- W4366996581 title "Time-shift selection for reservoir computing using a rank-revealing QR algorithm" @default.
- W4366996581 cites W1967783432 @default.
- W4366996581 cites W1977664984 @default.
- W4366996581 cites W1993248416 @default.
- W4366996581 cites W2008205484 @default.
- W4366996581 cites W2014683958 @default.
- W4366996581 cites W2022248835 @default.
- W4366996581 cites W2063562458 @default.
- W4366996581 cites W2103179919 @default.
- W4366996581 cites W2118706537 @default.
- W4366996581 cites W2128728535 @default.
- W4366996581 cites W2256527444 @default.
- W4366996581 cites W2333329341 @default.
- W4366996581 cites W2509987864 @default.
- W4366996581 cites W2580399228 @default.
- W4366996581 cites W2586258431 @default.
- W4366996581 cites W2587524409 @default.
- W4366996581 cites W2613833839 @default.
- W4366996581 cites W2627057354 @default.
- W4366996581 cites W2772397789 @default.
- W4366996581 cites W2782714865 @default.
- W4366996581 cites W2887258823 @default.
- W4366996581 cites W2898551707 @default.
- W4366996581 cites W2943844132 @default.
- W4366996581 cites W2963461769 @default.
- W4366996581 cites W2964065747 @default.
- W4366996581 cites W2970565811 @default.
- W4366996581 cites W2996678389 @default.
- W4366996581 cites W2998821156 @default.
- W4366996581 cites W3081010682 @default.
- W4366996581 cites W3101465594 @default.
- W4366996581 cites W3106056076 @default.
- W4366996581 cites W3153722619 @default.
- W4366996581 cites W3156859781 @default.
- W4366996581 cites W3174661051 @default.
- W4366996581 cites W3198294736 @default.
- W4366996581 cites W3202971499 @default.
- W4366996581 cites W3208812860 @default.
- W4366996581 cites W4200497803 @default.
- W4366996581 cites W4210524437 @default.
- W4366996581 cites W4237324918 @default.
- W4366996581 cites W4292181403 @default.
- W4366996581 doi "https://doi.org/10.1063/5.0141251" @default.
- W4366996581 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37097961" @default.
- W4366996581 hasPublicationYear "2023" @default.
- W4366996581 type Work @default.
- W4366996581 citedByCount "0" @default.
- W4366996581 crossrefType "journal-article" @default.
- W4366996581 hasAuthorship W4366996581A5020186212 @default.
- W4366996581 hasAuthorship W4366996581A5034065247 @default.
- W4366996581 hasAuthorship W4366996581A5063085099 @default.
- W4366996581 hasBestOaLocation W43669965812 @default.
- W4366996581 hasConcept C106487976 @default.
- W4366996581 hasConcept C11413529 @default.
- W4366996581 hasConcept C114614502 @default.
- W4366996581 hasConcept C121332964 @default.
- W4366996581 hasConcept C135796866 @default.
- W4366996581 hasConcept C147168706 @default.
- W4366996581 hasConcept C154945302 @default.
- W4366996581 hasConcept C158622935 @default.
- W4366996581 hasConcept C159985019 @default.
- W4366996581 hasConcept C162324750 @default.
- W4366996581 hasConcept C164226766 @default.
- W4366996581 hasConcept C187736073 @default.
- W4366996581 hasConcept C192562407 @default.
- W4366996581 hasConcept C2780451532 @default.
- W4366996581 hasConcept C33923547 @default.
- W4366996581 hasConcept C41008148 @default.
- W4366996581 hasConcept C50644808 @default.
- W4366996581 hasConcept C62520636 @default.
- W4366996581 hasConcept C81917197 @default.
- W4366996581 hasConceptScore W4366996581C106487976 @default.
- W4366996581 hasConceptScore W4366996581C11413529 @default.
- W4366996581 hasConceptScore W4366996581C114614502 @default.
- W4366996581 hasConceptScore W4366996581C121332964 @default.
- W4366996581 hasConceptScore W4366996581C135796866 @default.
- W4366996581 hasConceptScore W4366996581C147168706 @default.
- W4366996581 hasConceptScore W4366996581C154945302 @default.
- W4366996581 hasConceptScore W4366996581C158622935 @default.
- W4366996581 hasConceptScore W4366996581C159985019 @default.
- W4366996581 hasConceptScore W4366996581C162324750 @default.
- W4366996581 hasConceptScore W4366996581C164226766 @default.
- W4366996581 hasConceptScore W4366996581C187736073 @default.
- W4366996581 hasConceptScore W4366996581C192562407 @default.
- W4366996581 hasConceptScore W4366996581C2780451532 @default.
- W4366996581 hasConceptScore W4366996581C33923547 @default.
- W4366996581 hasConceptScore W4366996581C41008148 @default.
- W4366996581 hasConceptScore W4366996581C50644808 @default.
- W4366996581 hasConceptScore W4366996581C62520636 @default.
- W4366996581 hasConceptScore W4366996581C81917197 @default.
- W4366996581 hasFunder F4320332201 @default.
- W4366996581 hasIssue "4" @default.
- W4366996581 hasLocation W43669965811 @default.