Matches in SemOpenAlex for { <https://semopenalex.org/work/W2904136839> ?p ?o ?g. }
- W2904136839 endingPage "124" @default.
- W2904136839 startingPage "116" @default.
- W2904136839 abstract "Memristors have emerged as a potential tool to implement the training and operation of an integrated neural network, because of its current-voltage curve of the hysteresis loop and unique pulse regulation resistance method. However, most of the existing neural networks implemented on memristors are relatively basic architecture, and the processing functions are limited to the recognition of the simple signal and image models. In this paper, we propose a 3D Convolutional Neural Network based on memristor to recognize and classify the behaviors of human in the video with 6 main actions. As an extension of 2D Convolutional Neural Networks, 3D Convolutional Neural Networks have attracted attention for video information processing, since it introduces the time dimension innovatively on the basis of spatial dimensions to capture the contextual information between the different frames in the video. Accordingly, we use the 3D Convolution to construct our proposed neural network based on memristors. Besides, we use the basic 3 × 3 memristor arrays to construct the larger functional memristor arrays and form the 3D convolutional layers of our network by considering that the 3 × 3 basic memristor array has excellent flexibility and anti-jamming capability. With this strategy, we can make full use of the hardware structure to improve accuracy while reducing hardware noise. Finally, we implemented network obtain more than 70% accuracy on the Weizmann video dataset. This demonstration is an important step that memristors can implement the much larger and more complex neural networks for processing the more complex applications." @default.
- W2904136839 created "2018-12-22" @default.
- W2904136839 creator A5009238720 @default.
- W2904136839 creator A5019985419 @default.
- W2904136839 creator A5031050219 @default.
- W2904136839 creator A5045960607 @default.
- W2904136839 creator A5051239079 @default.
- W2904136839 date "2020-02-01" @default.
- W2904136839 modified "2023-10-10" @default.
- W2904136839 title "3D Convolutional Neural Network based on memristor for video recognition" @default.
- W2904136839 cites W1501531539 @default.
- W2904136839 cites W1526331010 @default.
- W2904136839 cites W1542981317 @default.
- W2904136839 cites W1983364832 @default.
- W2904136839 cites W2016922062 @default.
- W2904136839 cites W2026377462 @default.
- W2904136839 cites W2030971074 @default.
- W2904136839 cites W2055905702 @default.
- W2904136839 cites W2069991480 @default.
- W2904136839 cites W2120286148 @default.
- W2904136839 cites W2166243422 @default.
- W2904136839 cites W2225135580 @default.
- W2904136839 cites W2345812103 @default.
- W2904136839 cites W2389556795 @default.
- W2904136839 cites W2405945747 @default.
- W2904136839 cites W2504678134 @default.
- W2904136839 cites W2520861906 @default.
- W2904136839 cites W2522667948 @default.
- W2904136839 cites W2525649597 @default.
- W2904136839 cites W2526268316 @default.
- W2904136839 cites W2526646482 @default.
- W2904136839 cites W2533350959 @default.
- W2904136839 cites W2594785588 @default.
- W2904136839 cites W2607036705 @default.
- W2904136839 cites W2613205562 @default.
- W2904136839 cites W2760117628 @default.
- W2904136839 cites W2800761708 @default.
- W2904136839 cites W2963634791 @default.
- W2904136839 cites W2998915116 @default.
- W2904136839 doi "https://doi.org/10.1016/j.patrec.2018.12.005" @default.
- W2904136839 hasPublicationYear "2020" @default.
- W2904136839 type Work @default.
- W2904136839 sameAs 2904136839 @default.
- W2904136839 citedByCount "11" @default.
- W2904136839 countsByYear W29041368392019 @default.
- W2904136839 countsByYear W29041368392020 @default.
- W2904136839 countsByYear W29041368392021 @default.
- W2904136839 countsByYear W29041368392022 @default.
- W2904136839 crossrefType "journal-article" @default.
- W2904136839 hasAuthorship W2904136839A5009238720 @default.
- W2904136839 hasAuthorship W2904136839A5019985419 @default.
- W2904136839 hasAuthorship W2904136839A5031050219 @default.
- W2904136839 hasAuthorship W2904136839A5045960607 @default.
- W2904136839 hasAuthorship W2904136839A5051239079 @default.
- W2904136839 hasBestOaLocation W29041368391 @default.
- W2904136839 hasConcept C108583219 @default.
- W2904136839 hasConcept C119599485 @default.
- W2904136839 hasConcept C127413603 @default.
- W2904136839 hasConcept C150072547 @default.
- W2904136839 hasConcept C153180895 @default.
- W2904136839 hasConcept C154945302 @default.
- W2904136839 hasConcept C165801399 @default.
- W2904136839 hasConcept C182019814 @default.
- W2904136839 hasConcept C1895703 @default.
- W2904136839 hasConcept C24326235 @default.
- W2904136839 hasConcept C41008148 @default.
- W2904136839 hasConcept C50644808 @default.
- W2904136839 hasConcept C81363708 @default.
- W2904136839 hasConceptScore W2904136839C108583219 @default.
- W2904136839 hasConceptScore W2904136839C119599485 @default.
- W2904136839 hasConceptScore W2904136839C127413603 @default.
- W2904136839 hasConceptScore W2904136839C150072547 @default.
- W2904136839 hasConceptScore W2904136839C153180895 @default.
- W2904136839 hasConceptScore W2904136839C154945302 @default.
- W2904136839 hasConceptScore W2904136839C165801399 @default.
- W2904136839 hasConceptScore W2904136839C182019814 @default.
- W2904136839 hasConceptScore W2904136839C1895703 @default.
- W2904136839 hasConceptScore W2904136839C24326235 @default.
- W2904136839 hasConceptScore W2904136839C41008148 @default.
- W2904136839 hasConceptScore W2904136839C50644808 @default.
- W2904136839 hasConceptScore W2904136839C81363708 @default.
- W2904136839 hasFunder F4320312071 @default.
- W2904136839 hasFunder F4320313612 @default.
- W2904136839 hasFunder F4320321135 @default.
- W2904136839 hasFunder F4320326957 @default.
- W2904136839 hasFunder F4320337504 @default.
- W2904136839 hasLocation W29041368391 @default.
- W2904136839 hasLocation W29041368392 @default.
- W2904136839 hasOpenAccess W2904136839 @default.
- W2904136839 hasPrimaryLocation W29041368391 @default.
- W2904136839 hasRelatedWork W1543954628 @default.
- W2904136839 hasRelatedWork W2163054919 @default.
- W2904136839 hasRelatedWork W2185262500 @default.
- W2904136839 hasRelatedWork W2400934798 @default.
- W2904136839 hasRelatedWork W2401917269 @default.
- W2904136839 hasRelatedWork W2780290013 @default.
- W2904136839 hasRelatedWork W2797315502 @default.
- W2904136839 hasRelatedWork W3170109256 @default.