Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378086185> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W4378086185 abstract "Spiking neural networks (SNNs) have recently demonstrated outstanding performance in a variety of high-level tasks, such as image classification. However, advancements in the field of low-level assignments, such as image reconstruction, are rare. This may be due to the lack of promising image encoding techniques and corresponding neuromorphic devices designed specifically for SNN-based low-level vision problems. This paper begins by proposing a simple yet effective undistorted weighted-encoding-decoding technique, which primarily consists of an Undistorted Weighted-Encoding (UWE) and an Undistorted Weighted-Decoding (UWD). The former aims to convert a gray image into spike sequences for effective SNN learning, while the latter converts spike sequences back into images. Then, we design a new SNN training strategy, known as Independent-Temporal Backpropagation (ITBP) to avoid complex loss propagation in spatial and temporal dimensions, and experiments show that ITBP is superior to Spatio-Temporal Backpropagation (STBP). Finally, a so-called Virtual Temporal SNN (VTSNN) is formulated by incorporating the above-mentioned approaches into U-net network architecture, fully utilizing the potent multiscale representation capability. Experimental results on several commonly used datasets such as MNIST, F-MNIST, and CIFAR10 demonstrate that the proposed method produces competitive noise-removal performance extremely which is superior to the existing work. Compared to ANN with the same architecture, VTSNN has a greater chance of achieving superiority while consuming ~1/274 of the energy. Specifically, using the given encoding-decoding strategy, a simple neuromorphic circuit could be easily constructed to maximize this low-carbon strategy." @default.
- W4378086185 created "2023-05-25" @default.
- W4378086185 creator A5000096465 @default.
- W4378086185 creator A5023273273 @default.
- W4378086185 creator A5027563148 @default.
- W4378086185 creator A5031886937 @default.
- W4378086185 creator A5031972473 @default.
- W4378086185 creator A5088224232 @default.
- W4378086185 creator A5091293910 @default.
- W4378086185 date "2023-05-23" @default.
- W4378086185 modified "2023-09-30" @default.
- W4378086185 title "VTSNN: a virtual temporal spiking neural network" @default.
- W4378086185 cites W101771737 @default.
- W4378086185 cites W1985940938 @default.
- W4378086185 cites W1999085092 @default.
- W4378086185 cites W2042013578 @default.
- W4378086185 cites W2060561757 @default.
- W4378086185 cites W2109596721 @default.
- W4378086185 cites W2112796928 @default.
- W4378086185 cites W2116360511 @default.
- W4378086185 cites W2134251598 @default.
- W4378086185 cites W2149951190 @default.
- W4378086185 cites W2150355110 @default.
- W4378086185 cites W2569813014 @default.
- W4378086185 cites W2621826044 @default.
- W4378086185 cites W2783525259 @default.
- W4378086185 cites W2806066966 @default.
- W4378086185 cites W2977659243 @default.
- W4378086185 cites W2984844508 @default.
- W4378086185 cites W2990793844 @default.
- W4378086185 cites W3093471076 @default.
- W4378086185 cites W3124546450 @default.
- W4378086185 cites W3127197816 @default.
- W4378086185 cites W3182000414 @default.
- W4378086185 cites W3193561750 @default.
- W4378086185 cites W3206513151 @default.
- W4378086185 cites W3210805939 @default.
- W4378086185 cites W3212171552 @default.
- W4378086185 cites W4231081240 @default.
- W4378086185 doi "https://doi.org/10.3389/fnins.2023.1091097" @default.
- W4378086185 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37287800" @default.
- W4378086185 hasPublicationYear "2023" @default.
- W4378086185 type Work @default.
- W4378086185 citedByCount "0" @default.
- W4378086185 crossrefType "journal-article" @default.
- W4378086185 hasAuthorship W4378086185A5000096465 @default.
- W4378086185 hasAuthorship W4378086185A5023273273 @default.
- W4378086185 hasAuthorship W4378086185A5027563148 @default.
- W4378086185 hasAuthorship W4378086185A5031886937 @default.
- W4378086185 hasAuthorship W4378086185A5031972473 @default.
- W4378086185 hasAuthorship W4378086185A5088224232 @default.
- W4378086185 hasAuthorship W4378086185A5091293910 @default.
- W4378086185 hasBestOaLocation W43780861851 @default.
- W4378086185 hasConcept C11413529 @default.
- W4378086185 hasConcept C115903868 @default.
- W4378086185 hasConcept C11731999 @default.
- W4378086185 hasConcept C125411270 @default.
- W4378086185 hasConcept C151927369 @default.
- W4378086185 hasConcept C153180895 @default.
- W4378086185 hasConcept C154945302 @default.
- W4378086185 hasConcept C155032097 @default.
- W4378086185 hasConcept C190502265 @default.
- W4378086185 hasConcept C2781390188 @default.
- W4378086185 hasConcept C41008148 @default.
- W4378086185 hasConcept C50644808 @default.
- W4378086185 hasConcept C57273362 @default.
- W4378086185 hasConceptScore W4378086185C11413529 @default.
- W4378086185 hasConceptScore W4378086185C115903868 @default.
- W4378086185 hasConceptScore W4378086185C11731999 @default.
- W4378086185 hasConceptScore W4378086185C125411270 @default.
- W4378086185 hasConceptScore W4378086185C151927369 @default.
- W4378086185 hasConceptScore W4378086185C153180895 @default.
- W4378086185 hasConceptScore W4378086185C154945302 @default.
- W4378086185 hasConceptScore W4378086185C155032097 @default.
- W4378086185 hasConceptScore W4378086185C190502265 @default.
- W4378086185 hasConceptScore W4378086185C2781390188 @default.
- W4378086185 hasConceptScore W4378086185C41008148 @default.
- W4378086185 hasConceptScore W4378086185C50644808 @default.
- W4378086185 hasConceptScore W4378086185C57273362 @default.
- W4378086185 hasLocation W43780861851 @default.
- W4378086185 hasLocation W43780861852 @default.
- W4378086185 hasOpenAccess W4378086185 @default.
- W4378086185 hasPrimaryLocation W43780861851 @default.
- W4378086185 hasRelatedWork W2947957795 @default.
- W4378086185 hasRelatedWork W2963468148 @default.
- W4378086185 hasRelatedWork W2994834230 @default.
- W4378086185 hasRelatedWork W3161396968 @default.
- W4378086185 hasRelatedWork W3202412105 @default.
- W4378086185 hasRelatedWork W3214713078 @default.
- W4378086185 hasRelatedWork W4287639722 @default.
- W4378086185 hasRelatedWork W4288337556 @default.
- W4378086185 hasRelatedWork W4320813023 @default.
- W4378086185 hasRelatedWork W4378086185 @default.
- W4378086185 hasVolume "17" @default.
- W4378086185 isParatext "false" @default.
- W4378086185 isRetracted "false" @default.
- W4378086185 workType "article" @default.