FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3137378424> ?p ?o ?g. }

• W3137378424 abstract "A major characteristic of spiking neural networks (SNNs) over conventional artificial neural networks (ANNs) is their ability to spike, enabling them to use spike timing for coding and efficient computing. In this paper, we assess if neuromorphic datasets recorded from static images are able to evaluate the ability of SNNs to use spike timings in their calculations. We have analyzed N-MNIST, N-Caltech101 and DvsGesture along these lines, but focus our study on N-MNIST. First we evaluate if additional information is encoded in the time domain in a neuromorphic dataset. We show that an ANN trained with backpropagation on frame-based versions of N-MNIST and N-Caltech101 images achieve 99.23 and 78.01% accuracy. These are comparable to the state of the art—showing that an algorithm that purely works on spatial data can classify these datasets. Second we compare N-MNIST and DvsGesture on two STDP algorithms, RD-STDP, that can classify only spatial data, and STDP-tempotron that classifies spatiotemporal data. We demonstrate that RD-STDP performs very well on N-MNIST, while STDP-tempotron performs better on DvsGesture. Since DvsGesture has a temporal dimension, it requires STDP-tempotron, while N-MNIST can be adequately classified by an algorithm that works on spatial data alone. This shows that precise spike timings are not important in N-MNIST. N-MNIST does not, therefore, highlight the ability of SNNs to classify temporal data. The conclusions of this paper open the question—what dataset can evaluate SNN ability to classify temporal data?" @default.
• W3137378424 created "2021-03-29" @default.
• W3137378424 creator A5032690182 @default.
• W3137378424 creator A5066851412 @default.
• W3137378424 creator A5070294243 @default.
• W3137378424 date "2021-03-25" @default.
• W3137378424 modified "2023-10-11" @default.
• W3137378424 title "Is Neuromorphic MNIST Neuromorphic? Analyzing the Discriminative Power of Neuromorphic Datasets in the Time Domain" @default.
• W3137378424 cites W101771737 @default.
• W3137378424 cites W1120393922 @default.
• W3137378424 cites W1486852018 @default.
• W3137378424 cites W1570411240 @default.
• W3137378424 cites W1964380532 @default.
• W3137378424 cites W1967465676 @default.
• W3137378424 cites W1970578576 @default.
• W3137378424 cites W1975003449 @default.
• W3137378424 cites W1976993603 @default.
• W3137378424 cites W1980178290 @default.
• W3137378424 cites W2005235722 @default.
• W3137378424 cites W2009950336 @default.
• W3137378424 cites W2016574277 @default.
• W3137378424 cites W2020096355 @default.
• W3137378424 cites W2037030438 @default.
• W3137378424 cites W2057213277 @default.
• W3137378424 cites W2060561757 @default.
• W3137378424 cites W206948248 @default.
• W3137378424 cites W2073272844 @default.
• W3137378424 cites W2095397231 @default.
• W3137378424 cites W2097435621 @default.
• W3137378424 cites W2105848238 @default.
• W3137378424 cites W2107032718 @default.
• W3137378424 cites W2107662531 @default.
• W3137378424 cites W2112796928 @default.
• W3137378424 cites W2115831804 @default.
• W3137378424 cites W2121326391 @default.
• W3137378424 cites W2128432504 @default.
• W3137378424 cites W2129673518 @default.
• W3137378424 cites W2130360162 @default.
• W3137378424 cites W2132227527 @default.
• W3137378424 cites W2137278126 @default.
• W3137378424 cites W2138913040 @default.
• W3137378424 cites W2139295975 @default.
• W3137378424 cites W2144494088 @default.
• W3137378424 cites W2151035455 @default.
• W3137378424 cites W2155904486 @default.
• W3137378424 cites W2159353177 @default.
• W3137378424 cites W2159814546 @default.
• W3137378424 cites W2162827630 @default.
• W3137378424 cites W2168249605 @default.
• W3137378424 cites W2187011629 @default.
• W3137378424 cites W2268159046 @default.
• W3137378424 cites W2340032154 @default.
• W3137378424 cites W2343732617 @default.
• W3137378424 cites W2469278928 @default.
• W3137378424 cites W2477347005 @default.
• W3137378424 cites W2506959184 @default.
• W3137378424 cites W2513853720 @default.
• W3137378424 cites W2553470216 @default.
• W3137378424 cites W2621826044 @default.
• W3137378424 cites W2736299736 @default.
• W3137378424 cites W2745933219 @default.
• W3137378424 cites W2779025322 @default.
• W3137378424 cites W2805087868 @default.
• W3137378424 cites W2810358175 @default.
• W3137378424 cites W2886009882 @default.
• W3137378424 cites W2901297858 @default.
• W3137378424 cites W2942762614 @default.
• W3137378424 cites W2962804204 @default.
• W3137378424 cites W2963057320 @default.
• W3137378424 cites W2963144106 @default.
• W3137378424 cites W2963182550 @default.
• W3137378424 cites W2963305465 @default.
• W3137378424 cites W2971854498 @default.
• W3137378424 cites W2974328520 @default.
• W3137378424 cites W2986821012 @default.
• W3137378424 cites W3007283957 @default.
• W3137378424 cites W3010268791 @default.
• W3137378424 cites W3015205410 @default.
• W3137378424 cites W3018523095 @default.
• W3137378424 cites W3025773901 @default.
• W3137378424 cites W3065747603 @default.
• W3137378424 cites W3091191559 @default.
• W3137378424 cites W3102087395 @default.
• W3137378424 cites W3122510310 @default.
• W3137378424 cites W4233125481 @default.
• W3137378424 cites W4246583157 @default.
• W3137378424 cites W4253319473 @default.
• W3137378424 doi "https://doi.org/10.3389/fnins.2021.608567" @default.
• W3137378424 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8027306" @default.
• W3137378424 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33841072" @default.
• W3137378424 hasPublicationYear "2021" @default.
• W3137378424 type Work @default.
• W3137378424 sameAs 3137378424 @default.
• W3137378424 citedByCount "12" @default.
• W3137378424 countsByYear W31373784242021 @default.
• W3137378424 countsByYear W31373784242022 @default.
• W3137378424 countsByYear W31373784242023 @default.
• W3137378424 crossrefType "journal-article" @default.
• W3137378424 hasAuthorship W3137378424A5032690182 @default.
• W3137378424 hasAuthorship W3137378424A5066851412 @default.

• next