FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4211210730> ?p ?o ?g. }

• W4211210730 endingPage "194" @default.
• W4211210730 startingPage "184" @default.
• W4211210730 abstract "Bio-inspired recipes are being introduced to artificial neural networks for the efficient processing of spatio-temporal tasks. Among them, Leaky Integrate and Fire (LIF) model is the most remarkable one thanks to its temporal processing capability, lightweight model structure, and well investigated direct training methods. However, most learnable LIF networks generally take neurons as independent individuals that communicate via chemical synapses, leaving electrical synapses all behind. On the contrary, it has been well investigated in biological neural networks that the inter-neuron electrical synapse takes a great effect on the coordination and synchronization of generating action potentials. In this work, we are engaged in modeling such electrical synapses in artificial LIF neurons, where membrane potentials propagate to neighbor neurons via convolution operations, and the refined neural model ECLIF is proposed. We then build deep networks using ECLIF and trained them using a back-propagation-through-time algorithm. We found that the proposed network has great accuracy improvement over traditional LIF on five datasets and achieves high accuracy on them. In conclusion, it reveals that the introduction of the electrical synapse is an important factor for achieving high accuracy on realistic spatio-temporal tasks." @default.
• W4211210730 created "2022-02-13" @default.
• W4211210730 creator A5030833954 @default.
• W4211210730 creator A5035488023 @default.
• W4211210730 creator A5039331830 @default.
• W4211210730 creator A5045148628 @default.
• W4211210730 creator A5047515983 @default.
• W4211210730 creator A5059925667 @default.
• W4211210730 creator A5071540153 @default.
• W4211210730 date "2022-05-01" @default.
• W4211210730 modified "2023-10-14" @default.
• W4211210730 title "Modeling learnable electrical synapse for high precision spatio-temporal recognition" @default.
• W4211210730 cites W1547993237 @default.
• W4211210730 cites W1570411240 @default.
• W4211210730 cites W179875071 @default.
• W4211210730 cites W1881709150 @default.
• W4211210730 cites W1990323937 @default.
• W4211210730 cites W2007431958 @default.
• W4211210730 cites W2026372417 @default.
• W4211210730 cites W2064675550 @default.
• W4211210730 cites W2066188896 @default.
• W4211210730 cites W2076964542 @default.
• W4211210730 cites W2128949090 @default.
• W4211210730 cites W2130459697 @default.
• W4211210730 cites W2141166794 @default.
• W4211210730 cites W2152809909 @default.
• W4211210730 cites W2156432573 @default.
• W4211210730 cites W2157239334 @default.
• W4211210730 cites W2194775991 @default.
• W4211210730 cites W2469278928 @default.
• W4211210730 cites W2513853720 @default.
• W4211210730 cites W2516444268 @default.
• W4211210730 cites W2619510810 @default.
• W4211210730 cites W2621826044 @default.
• W4211210730 cites W2743130883 @default.
• W4211210730 cites W2745933219 @default.
• W4211210730 cites W2775079417 @default.
• W4211210730 cites W2796051767 @default.
• W4211210730 cites W2796323669 @default.
• W4211210730 cites W2798878556 @default.
• W4211210730 cites W2892077605 @default.
• W4211210730 cites W2898323475 @default.
• W4211210730 cites W2944546415 @default.
• W4211210730 cites W2946092987 @default.
• W4211210730 cites W2963510238 @default.
• W4211210730 cites W2967821093 @default.
• W4211210730 cites W2971854498 @default.
• W4211210730 cites W2974328520 @default.
• W4211210730 cites W2984844508 @default.
• W4211210730 cites W2986864699 @default.
• W4211210730 cites W2990793844 @default.
• W4211210730 cites W3016391357 @default.
• W4211210730 cites W3019438330 @default.
• W4211210730 cites W3021913097 @default.
• W4211210730 cites W3022766987 @default.
• W4211210730 cites W3035400263 @default.
• W4211210730 cites W3046044791 @default.
• W4211210730 cites W3093388624 @default.
• W4211210730 cites W3124478039 @default.
• W4211210730 doi "https://doi.org/10.1016/j.neunet.2022.02.006" @default.
• W4211210730 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35248808" @default.
• W4211210730 hasPublicationYear "2022" @default.
• W4211210730 type Work @default.
• W4211210730 citedByCount "2" @default.
• W4211210730 countsByYear W42112107302022 @default.
• W4211210730 countsByYear W42112107302023 @default.
• W4211210730 crossrefType "journal-article" @default.
• W4211210730 hasAuthorship W4211210730A5030833954 @default.
• W4211210730 hasAuthorship W4211210730A5035488023 @default.
• W4211210730 hasAuthorship W4211210730A5039331830 @default.
• W4211210730 hasAuthorship W4211210730A5045148628 @default.
• W4211210730 hasAuthorship W4211210730A5047515983 @default.
• W4211210730 hasAuthorship W4211210730A5059925667 @default.
• W4211210730 hasAuthorship W4211210730A5071540153 @default.
• W4211210730 hasConcept C108583219 @default.
• W4211210730 hasConcept C127162648 @default.
• W4211210730 hasConcept C127445978 @default.
• W4211210730 hasConcept C153180895 @default.
• W4211210730 hasConcept C154945302 @default.
• W4211210730 hasConcept C158157758 @default.
• W4211210730 hasConcept C169760540 @default.
• W4211210730 hasConcept C2778562939 @default.
• W4211210730 hasConcept C2908872077 @default.
• W4211210730 hasConcept C41008148 @default.
• W4211210730 hasConcept C45347329 @default.
• W4211210730 hasConcept C50644808 @default.
• W4211210730 hasConcept C76155785 @default.
• W4211210730 hasConcept C79879829 @default.
• W4211210730 hasConcept C86803240 @default.
• W4211210730 hasConcept C95444343 @default.
• W4211210730 hasConceptScore W4211210730C108583219 @default.
• W4211210730 hasConceptScore W4211210730C127162648 @default.
• W4211210730 hasConceptScore W4211210730C127445978 @default.
• W4211210730 hasConceptScore W4211210730C153180895 @default.
• W4211210730 hasConceptScore W4211210730C154945302 @default.
• W4211210730 hasConceptScore W4211210730C158157758 @default.
• W4211210730 hasConceptScore W4211210730C169760540 @default.
• W4211210730 hasConceptScore W4211210730C2778562939 @default.

• next