FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292574980> ?p ?o ?g. }

• W4292574980 abstract "Artificial neural networks (ANNs) are the basis of recent advances in artificial intelligence (AI); they typically use real valued neuron responses. By contrast, biological neurons are known to operate using spike trains. In principle, spiking neural networks (SNNs) may have a greater representational capability than ANNs, especially for time series such as speech; however their adoption has been held back by both a lack of stable training algorithms and a lack of compatible baselines. We begin with a fairly thorough review of literature around the conjunction of ANNs and SNNs. Focusing on surrogate gradient approaches, we proceed to define a simple but relevant evaluation based on recent speech command tasks. After evaluating a representative selection of architectures, we show that a combination of adaptation, recurrence and surrogate gradients can yield light spiking architectures that are not only able to compete with ANN solutions, but also retain a high degree of compatibility with them in modern deep learning frameworks. We conclude tangibly that SNNs are appropriate for future research in AI, in particular for speech processing applications, and more speculatively that they may also assist in inference about biological function." @default.
• W4292574980 created "2022-08-22" @default.
• W4292574980 creator A5034575773 @default.
• W4292574980 creator A5081808619 @default.
• W4292574980 date "2022-08-22" @default.
• W4292574980 modified "2023-10-09" @default.
• W4292574980 title "A surrogate gradient spiking baseline for speech command recognition" @default.
• W4292574980 cites W101771737 @default.
• W4292574980 cites W1975003449 @default.
• W4292574980 cites W1985940938 @default.
• W4292574980 cites W2006581331 @default.
• W4292574980 cites W2009375605 @default.
• W4292574980 cites W2025881996 @default.
• W4292574980 cites W2026694347 @default.
• W4292574980 cites W2037030438 @default.
• W4292574980 cites W2046424015 @default.
• W4292574980 cites W2048967079 @default.
• W4292574980 cites W2062899906 @default.
• W4292574980 cites W2064675550 @default.
• W4292574980 cites W2065158671 @default.
• W4292574980 cites W2076856047 @default.
• W4292574980 cites W2083145261 @default.
• W4292574980 cites W2109234859 @default.
• W4292574980 cites W2110316244 @default.
• W4292574980 cites W2117726420 @default.
• W4292574980 cites W2121071186 @default.
• W4292574980 cites W2127388521 @default.
• W4292574980 cites W2128949090 @default.
• W4292574980 cites W2139413555 @default.
• W4292574980 cites W2144993394 @default.
• W4292574980 cites W2146545384 @default.
• W4292574980 cites W2150474797 @default.
• W4292574980 cites W2156581621 @default.
• W4292574980 cites W2164653071 @default.
• W4292574980 cites W2271476098 @default.
• W4292574980 cites W2281943757 @default.
• W4292574980 cites W2293968535 @default.
• W4292574980 cites W2512805308 @default.
• W4292574980 cites W2569813014 @default.
• W4292574980 cites W2783525259 @default.
• W4292574980 cites W2794209590 @default.
• W4292574980 cites W2888850715 @default.
• W4292574980 cites W2898323475 @default.
• W4292574980 cites W2901937441 @default.
• W4292574980 cites W2924112519 @default.
• W4292574980 cites W2963335874 @default.
• W4292574980 cites W2963406173 @default.
• W4292574980 cites W2963820107 @default.
• W4292574980 cites W2980513133 @default.
• W4292574980 cites W2982265383 @default.
• W4292574980 cites W2984844508 @default.
• W4292574980 cites W2990793844 @default.
• W4292574980 cites W3005319366 @default.
• W4292574980 cites W3010670467 @default.
• W4292574980 cites W3010748916 @default.
• W4292574980 cites W3023212902 @default.
• W4292574980 cites W3025581723 @default.
• W4292574980 cites W3025773901 @default.
• W4292574980 cites W3027324516 @default.
• W4292574980 cites W3038819247 @default.
• W4292574980 cites W3046044791 @default.
• W4292574980 cites W3098773154 @default.
• W4292574980 cites W3101210313 @default.
• W4292574980 cites W3102087395 @default.
• W4292574980 cites W3110073026 @default.
• W4292574980 cites W3158770455 @default.
• W4292574980 cites W3161335276 @default.
• W4292574980 cites W3180917267 @default.
• W4292574980 cites W3185986431 @default.
• W4292574980 cites W3186962187 @default.
• W4292574980 cites W3196974791 @default.
• W4292574980 cites W3203906445 @default.
• W4292574980 cites W3206817059 @default.
• W4292574980 cites W4238614602 @default.
• W4292574980 cites W4255229883 @default.
• W4292574980 doi "https://doi.org/10.3389/fnins.2022.865897" @default.
• W4292574980 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36117617" @default.
• W4292574980 hasPublicationYear "2022" @default.
• W4292574980 type Work @default.
• W4292574980 citedByCount "5" @default.
• W4292574980 countsByYear W42925749802022 @default.
• W4292574980 countsByYear W42925749802023 @default.
• W4292574980 crossrefType "journal-article" @default.
• W4292574980 hasAuthorship W4292574980A5034575773 @default.
• W4292574980 hasAuthorship W4292574980A5081808619 @default.
• W4292574980 hasBestOaLocation W42925749801 @default.
• W4292574980 hasConcept C115903868 @default.
• W4292574980 hasConcept C11731999 @default.
• W4292574980 hasConcept C119857082 @default.
• W4292574980 hasConcept C154945302 @default.
• W4292574980 hasConcept C2776214188 @default.
• W4292574980 hasConcept C2781390188 @default.
• W4292574980 hasConcept C41008148 @default.
• W4292574980 hasConcept C50644808 @default.
• W4292574980 hasConceptScore W4292574980C115903868 @default.
• W4292574980 hasConceptScore W4292574980C11731999 @default.
• W4292574980 hasConceptScore W4292574980C119857082 @default.
• W4292574980 hasConceptScore W4292574980C154945302 @default.
• W4292574980 hasConceptScore W4292574980C2776214188 @default.
• W4292574980 hasConceptScore W4292574980C2781390188 @default.

• next