FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3017769710> ?p ?o ?g. }

• W3017769710 endingPage "23" @default.
• W3017769710 startingPage "12" @default.
• W3017769710 abstract "Spiking neural networks (SNNs) are believed to be a powerful neural computation framework inspired by the vivo neurons. As a class of recurrent SNNs, liquid state machines (LSMs) are biologically more plausible models imitating the architecture and functions of the human brain for information processing. However, few LSM models can outperform conventional analogue neural networks for solving real-world classification or regression problems, which can mainly be attributed to the sensitivity of the training performance to the architecture of the reservoir and the parameters in the spiking neuron models. Most recently, many algorithms have been proposed for automated machine learning that aims to automatically design the architecture and parameters of deep neural networks without much human intervention. Although automated machine learning and neural architecture search have been extremely successful in conventional neural networks, little research on search for an optimal architecture and hyperparameters of LSMs has been reported. This work proposes on a surrogate-assisted evolutionary search method for optimization of the hyperparameters and neural architecture of the reservoir of LSMs using the covariance matrix adaptation evolution strategy (CMA-ES). For reducing the search space, the architecture of the LSM is encoded by a connectivity probability together with the hyperparameters in the spiking neuron models. To enhance the computational efficiency, a Gaussian process is adopted as the surrogate to assist the CMA-ES. The proposed GP-assisted CMA-ES is compared with the canonical CMA-ES and a Bayesian optimization algorithm on two popular datasets including image and action recognition. Our results confirm that the proposed algorithm is efficient and effective in optimizing the parameters and architecture of LSMs." @default.
• W3017769710 created "2020-05-01" @default.
• W3017769710 creator A5001593753 @default.
• W3017769710 creator A5022740106 @default.
• W3017769710 creator A5032314861 @default.
• W3017769710 date "2020-09-01" @default.
• W3017769710 modified "2023-10-14" @default.
• W3017769710 title "Surrogate-Assisted Evolutionary Search of Spiking Neural Architectures in Liquid State Machines" @default.
• W3017769710 cites W101771737 @default.
• W3017769710 cites W1486852018 @default.
• W3017769710 cites W1570411240 @default.
• W3017769710 cites W1786326374 @default.
• W3017769710 cites W1964357027 @default.
• W3017769710 cites W1988976106 @default.
• W3017769710 cites W2004168727 @default.
• W3017769710 cites W2011174137 @default.
• W3017769710 cites W2030568230 @default.
• W3017769710 cites W2086066258 @default.
• W3017769710 cites W2103179919 @default.
• W3017769710 cites W2110194546 @default.
• W3017769710 cites W2112036188 @default.
• W3017769710 cites W2112796928 @default.
• W3017769710 cites W2145339207 @default.
• W3017769710 cites W2152637387 @default.
• W3017769710 cites W2166739626 @default.
• W3017769710 cites W2192203593 @default.
• W3017769710 cites W2239861374 @default.
• W3017769710 cites W2257979135 @default.
• W3017769710 cites W2513853720 @default.
• W3017769710 cites W2588977645 @default.
• W3017769710 cites W2593472350 @default.
• W3017769710 cites W2593980914 @default.
• W3017769710 cites W2621826044 @default.
• W3017769710 cites W2774743895 @default.
• W3017769710 cites W2785988364 @default.
• W3017769710 cites W2806066966 @default.
• W3017769710 cites W2808550672 @default.
• W3017769710 cites W2891140334 @default.
• W3017769710 cites W2891186800 @default.
• W3017769710 cites W2936345093 @default.
• W3017769710 doi "https://doi.org/10.1016/j.neucom.2020.04.079" @default.
• W3017769710 hasPublicationYear "2020" @default.
• W3017769710 type Work @default.
• W3017769710 sameAs 3017769710 @default.
• W3017769710 citedByCount "20" @default.
• W3017769710 countsByYear W30177697102020 @default.
• W3017769710 countsByYear W30177697102021 @default.
• W3017769710 countsByYear W30177697102022 @default.
• W3017769710 countsByYear W30177697102023 @default.
• W3017769710 crossrefType "journal-article" @default.
• W3017769710 hasAuthorship W3017769710A5001593753 @default.
• W3017769710 hasAuthorship W3017769710A5022740106 @default.
• W3017769710 hasAuthorship W3017769710A5032314861 @default.
• W3017769710 hasConcept C11731999 @default.
• W3017769710 hasConcept C119857082 @default.
• W3017769710 hasConcept C121332964 @default.
• W3017769710 hasConcept C131675550 @default.
• W3017769710 hasConcept C154945302 @default.
• W3017769710 hasConcept C159149176 @default.
• W3017769710 hasConcept C163716315 @default.
• W3017769710 hasConcept C205555498 @default.
• W3017769710 hasConcept C207002847 @default.
• W3017769710 hasConcept C2778049539 @default.
• W3017769710 hasConcept C41008148 @default.
• W3017769710 hasConcept C50644808 @default.
• W3017769710 hasConcept C61326573 @default.
• W3017769710 hasConcept C62520636 @default.
• W3017769710 hasConcept C8642999 @default.
• W3017769710 hasConceptScore W3017769710C11731999 @default.
• W3017769710 hasConceptScore W3017769710C119857082 @default.
• W3017769710 hasConceptScore W3017769710C121332964 @default.
• W3017769710 hasConceptScore W3017769710C131675550 @default.
• W3017769710 hasConceptScore W3017769710C154945302 @default.
• W3017769710 hasConceptScore W3017769710C159149176 @default.
• W3017769710 hasConceptScore W3017769710C163716315 @default.
• W3017769710 hasConceptScore W3017769710C205555498 @default.
• W3017769710 hasConceptScore W3017769710C207002847 @default.
• W3017769710 hasConceptScore W3017769710C2778049539 @default.
• W3017769710 hasConceptScore W3017769710C41008148 @default.
• W3017769710 hasConceptScore W3017769710C50644808 @default.
• W3017769710 hasConceptScore W3017769710C61326573 @default.
• W3017769710 hasConceptScore W3017769710C62520636 @default.
• W3017769710 hasConceptScore W3017769710C8642999 @default.
• W3017769710 hasFunder F4320321001 @default.
• W3017769710 hasLocation W30177697101 @default.
• W3017769710 hasOpenAccess W3017769710 @default.
• W3017769710 hasPrimaryLocation W30177697101 @default.
• W3017769710 hasRelatedWork W1569788011 @default.
• W3017769710 hasRelatedWork W2903759548 @default.
• W3017769710 hasRelatedWork W2988011443 @default.
• W3017769710 hasRelatedWork W3017769710 @default.
• W3017769710 hasRelatedWork W3113131953 @default.
• W3017769710 hasRelatedWork W3129764450 @default.
• W3017769710 hasRelatedWork W3199608561 @default.
• W3017769710 hasRelatedWork W4296591856 @default.
• W3017769710 hasRelatedWork W4298052809 @default.
• W3017769710 hasRelatedWork W4360619614 @default.
• W3017769710 hasVolume "406" @default.

• next