FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3102087395> ?p ?o ?g. }

• W3102087395 endingPage "1541" @default.
• W3102087395 startingPage "1514" @default.
• W3102087395 abstract "A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns." @default.
• W3102087395 created "2020-11-23" @default.
• W3102087395 creator A5001875800 @default.
• W3102087395 creator A5056551357 @default.
• W3102087395 date "2018-06-01" @default.
• W3102087395 modified "2023-10-17" @default.
• W3102087395 title "SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks" @default.
• W3102087395 cites W1484004770 @default.
• W3102087395 cites W1570411240 @default.
• W3102087395 cites W1970109917 @default.
• W3102087395 cites W2001218774 @default.
• W3102087395 cites W2003357516 @default.
• W3102087395 cites W2009839417 @default.
• W3102087395 cites W2016589492 @default.
• W3102087395 cites W2016708835 @default.
• W3102087395 cites W2024152195 @default.
• W3102087395 cites W2025166739 @default.
• W3102087395 cites W2025546714 @default.
• W3102087395 cites W2043951469 @default.
• W3102087395 cites W2054113233 @default.
• W3102087395 cites W2058616551 @default.
• W3102087395 cites W2069845225 @default.
• W3102087395 cites W2069873783 @default.
• W3102087395 cites W2076063813 @default.
• W3102087395 cites W2082660315 @default.
• W3102087395 cites W2084259975 @default.
• W3102087395 cites W2085016237 @default.
• W3102087395 cites W2091845343 @default.
• W3102087395 cites W2093002383 @default.
• W3102087395 cites W2103179919 @default.
• W3102087395 cites W2107362261 @default.
• W3102087395 cites W2107696819 @default.
• W3102087395 cites W2111562869 @default.
• W3102087395 cites W2115831804 @default.
• W3102087395 cites W2127388521 @default.
• W3102087395 cites W2128367023 @default.
• W3102087395 cites W2142770417 @default.
• W3102087395 cites W2154616847 @default.
• W3102087395 cites W2165639766 @default.
• W3102087395 cites W2169604063 @default.
• W3102087395 cites W2171236529 @default.
• W3102087395 cites W2239861374 @default.
• W3102087395 cites W2271476098 @default.
• W3102087395 cites W2276533724 @default.
• W3102087395 cites W2281943757 @default.
• W3102087395 cites W2284177166 @default.
• W3102087395 cites W2290982066 @default.
• W3102087395 cites W2293092608 @default.
• W3102087395 cites W2432567885 @default.
• W3102087395 cites W2510122185 @default.
• W3102087395 cites W2529004582 @default.
• W3102087395 cites W2552737632 @default.
• W3102087395 cites W2554917868 @default.
• W3102087395 cites W2569813014 @default.
• W3102087395 cites W2611608598 @default.
• W3102087395 cites W2753961618 @default.
• W3102087395 cites W2919115771 @default.
• W3102087395 cites W2950535698 @default.
• W3102087395 cites W2951065015 @default.
• W3102087395 cites W2963416336 @default.
• W3102087395 cites W2964017885 @default.
• W3102087395 cites W3010800952 @default.
• W3102087395 cites W386569623 @default.
• W3102087395 cites W4231081240 @default.
• W3102087395 cites W4242770316 @default.
• W3102087395 doi "https://doi.org/10.1162/neco_a_01086" @default.
• W3102087395 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6118408" @default.
• W3102087395 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29652587" @default.
• W3102087395 hasPublicationYear "2018" @default.
• W3102087395 type Work @default.
• W3102087395 sameAs 3102087395 @default.
• W3102087395 citedByCount "338" @default.
• W3102087395 countsByYear W31020873952017 @default.
• W3102087395 countsByYear W31020873952018 @default.
• W3102087395 countsByYear W31020873952019 @default.
• W3102087395 countsByYear W31020873952020 @default.
• W3102087395 countsByYear W31020873952021 @default.
• W3102087395 countsByYear W31020873952022 @default.
• W3102087395 countsByYear W31020873952023 @default.
• W3102087395 crossrefType "journal-article" @default.
• W3102087395 hasAuthorship W3102087395A5001875800 @default.
• W3102087395 hasAuthorship W3102087395A5056551357 @default.
• W3102087395 hasBestOaLocation W31020873952 @default.
• W3102087395 hasConcept C11413529 @default.
• W3102087395 hasConcept C115903868 @default.
• W3102087395 hasConcept C11731999 @default.
• W3102087395 hasConcept C118403218 @default.
• W3102087395 hasConcept C119857082 @default.
• W3102087395 hasConcept C121332964 @default.
• W3102087395 hasConcept C136389625 @default.
• W3102087395 hasConcept C154945302 @default.
• W3102087395 hasConcept C158622935 @default.
• W3102087395 hasConcept C2779127903 @default.
• W3102087395 hasConcept C2781390188 @default.
• W3102087395 hasConcept C33010914 @default.
• W3102087395 hasConcept C3832189 @default.
• W3102087395 hasConcept C41008148 @default.
• W3102087395 hasConcept C45374587 @default.

• next