Matches in SemOpenAlex for { <https://semopenalex.org/work/W3033301241> ?p ?o ?g. }
- W3033301241 endingPage "21" @default.
- W3033301241 startingPage "11" @default.
- W3033301241 abstract "Deep neural networks (DNNs) have achieved outstanding performance in a wide range of applications, e.g., image classification, natural language processing, etc. Despite the good performance, the huge number of parameters in DNNs brings challenges to efficient training of DNNs and also their deployment in low-end devices with limited computing resources. In this paper, we explore the correlations in the weight matrices, and approximate the weight matrices with the low-rank block-term tensors. We name the new corresponding structure as block-term tensor layers (BT-layers), which can be easily adapted to neural network models, such as CNNs and RNNs. In particular, the inputs and the outputs in BT-layers are reshaped into low-dimensional high-order tensors with a similar or improved representation power. Sufficient experiments have demonstrated that BT-layers in CNNs and RNNs can achieve a very large compression ratio on the number of parameters while preserving or improving the representation power of the original DNNs." @default.
- W3033301241 created "2020-06-12" @default.
- W3033301241 creator A5024663093 @default.
- W3033301241 creator A5031574868 @default.
- W3033301241 creator A5051227924 @default.
- W3033301241 creator A5054050815 @default.
- W3033301241 creator A5062753948 @default.
- W3033301241 creator A5081662508 @default.
- W3033301241 date "2020-10-01" @default.
- W3033301241 modified "2023-10-05" @default.
- W3033301241 title "Block-term tensor neural networks" @default.
- W3033301241 cites W1963826206 @default.
- W3033301241 cites W1993482030 @default.
- W3033301241 cites W2000045479 @default.
- W3033301241 cites W2000215628 @default.
- W3033301241 cites W2040006565 @default.
- W3033301241 cites W2040376026 @default.
- W3033301241 cites W2076063813 @default.
- W3033301241 cites W2104636679 @default.
- W3033301241 cites W2112796928 @default.
- W3033301241 cites W2150355110 @default.
- W3033301241 cites W2194775991 @default.
- W3033301241 cites W2516041031 @default.
- W3033301241 cites W2753545915 @default.
- W3033301241 cites W2888987473 @default.
- W3033301241 cites W2889186417 @default.
- W3033301241 cites W2949615858 @default.
- W3033301241 cites W2963334029 @default.
- W3033301241 cites W2966234499 @default.
- W3033301241 cites W2978451921 @default.
- W3033301241 cites W3099497510 @default.
- W3033301241 cites W3103713775 @default.
- W3033301241 doi "https://doi.org/10.1016/j.neunet.2020.05.034" @default.
- W3033301241 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32589587" @default.
- W3033301241 hasPublicationYear "2020" @default.
- W3033301241 type Work @default.
- W3033301241 sameAs 3033301241 @default.
- W3033301241 citedByCount "17" @default.
- W3033301241 countsByYear W30333012412021 @default.
- W3033301241 countsByYear W30333012412022 @default.
- W3033301241 countsByYear W30333012412023 @default.
- W3033301241 crossrefType "journal-article" @default.
- W3033301241 hasAuthorship W3033301241A5024663093 @default.
- W3033301241 hasAuthorship W3033301241A5031574868 @default.
- W3033301241 hasAuthorship W3033301241A5051227924 @default.
- W3033301241 hasAuthorship W3033301241A5054050815 @default.
- W3033301241 hasAuthorship W3033301241A5062753948 @default.
- W3033301241 hasAuthorship W3033301241A5081662508 @default.
- W3033301241 hasBestOaLocation W30333012412 @default.
- W3033301241 hasConcept C11413529 @default.
- W3033301241 hasConcept C114614502 @default.
- W3033301241 hasConcept C121332964 @default.
- W3033301241 hasConcept C153180895 @default.
- W3033301241 hasConcept C154945302 @default.
- W3033301241 hasConcept C155281189 @default.
- W3033301241 hasConcept C159985019 @default.
- W3033301241 hasConcept C163258240 @default.
- W3033301241 hasConcept C164226766 @default.
- W3033301241 hasConcept C17744445 @default.
- W3033301241 hasConcept C192562407 @default.
- W3033301241 hasConcept C199539241 @default.
- W3033301241 hasConcept C202444582 @default.
- W3033301241 hasConcept C204323151 @default.
- W3033301241 hasConcept C2776359362 @default.
- W3033301241 hasConcept C2777210771 @default.
- W3033301241 hasConcept C33923547 @default.
- W3033301241 hasConcept C41008148 @default.
- W3033301241 hasConcept C50644808 @default.
- W3033301241 hasConcept C61797465 @default.
- W3033301241 hasConcept C62520636 @default.
- W3033301241 hasConcept C80444323 @default.
- W3033301241 hasConcept C94625758 @default.
- W3033301241 hasConceptScore W3033301241C11413529 @default.
- W3033301241 hasConceptScore W3033301241C114614502 @default.
- W3033301241 hasConceptScore W3033301241C121332964 @default.
- W3033301241 hasConceptScore W3033301241C153180895 @default.
- W3033301241 hasConceptScore W3033301241C154945302 @default.
- W3033301241 hasConceptScore W3033301241C155281189 @default.
- W3033301241 hasConceptScore W3033301241C159985019 @default.
- W3033301241 hasConceptScore W3033301241C163258240 @default.
- W3033301241 hasConceptScore W3033301241C164226766 @default.
- W3033301241 hasConceptScore W3033301241C17744445 @default.
- W3033301241 hasConceptScore W3033301241C192562407 @default.
- W3033301241 hasConceptScore W3033301241C199539241 @default.
- W3033301241 hasConceptScore W3033301241C202444582 @default.
- W3033301241 hasConceptScore W3033301241C204323151 @default.
- W3033301241 hasConceptScore W3033301241C2776359362 @default.
- W3033301241 hasConceptScore W3033301241C2777210771 @default.
- W3033301241 hasConceptScore W3033301241C33923547 @default.
- W3033301241 hasConceptScore W3033301241C41008148 @default.
- W3033301241 hasConceptScore W3033301241C50644808 @default.
- W3033301241 hasConceptScore W3033301241C61797465 @default.
- W3033301241 hasConceptScore W3033301241C62520636 @default.
- W3033301241 hasConceptScore W3033301241C80444323 @default.
- W3033301241 hasConceptScore W3033301241C94625758 @default.
- W3033301241 hasFunder F4320335777 @default.
- W3033301241 hasLocation W30333012411 @default.
- W3033301241 hasLocation W30333012412 @default.