Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317525906> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4317525906 endingPage "219" @default.
- W4317525906 startingPage "209" @default.
- W4317525906 abstract "Model compression technology investigates the compression of deep neural networks by quantizing the full-precision weights of the network into low-bit ones, to achieve network acceleration. However, most of the existing quantization operations are calculated by simple thresholding operations, which will lead to serious precision loss. In this paper, we propose a new quantization framework combined with pruning, called Multiple Residual Quantization of Pruning (MRQP), to achieve higher precision quantization neural network (QNN). MRQP recursively performs quantization of the full-precision weights by combining the low-bit weights stem and residual parts many times, to minimize the error between the quantized weights and the full-precision weights, and to ensure higher precision quantization. At the same time, MRQP prunes some weights that have less impact on loss function to further reduce model size." @default.
- W4317525906 created "2023-01-20" @default.
- W4317525906 creator A5008844053 @default.
- W4317525906 creator A5038704690 @default.
- W4317525906 creator A5059983248 @default.
- W4317525906 creator A5068061222 @default.
- W4317525906 creator A5074042241 @default.
- W4317525906 date "2022-01-01" @default.
- W4317525906 modified "2023-10-18" @default.
- W4317525906 title "Multiple Residual Quantization of Pruning" @default.
- W4317525906 cites W2140655807 @default.
- W4317525906 cites W2300242332 @default.
- W4317525906 cites W2740985535 @default.
- W4317525906 cites W2796679222 @default.
- W4317525906 cites W2884150179 @default.
- W4317525906 cites W2898968651 @default.
- W4317525906 cites W2912581782 @default.
- W4317525906 cites W2912886600 @default.
- W4317525906 cites W2962939807 @default.
- W4317525906 cites W2965862774 @default.
- W4317525906 cites W2970413753 @default.
- W4317525906 cites W2973096946 @default.
- W4317525906 cites W2981868774 @default.
- W4317525906 cites W2999803881 @default.
- W4317525906 cites W3000881061 @default.
- W4317525906 cites W3031696893 @default.
- W4317525906 cites W3034719990 @default.
- W4317525906 cites W3034795332 @default.
- W4317525906 cites W3123270512 @default.
- W4317525906 cites W3156544519 @default.
- W4317525906 cites W3173877717 @default.
- W4317525906 cites W3181252431 @default.
- W4317525906 cites W3201829457 @default.
- W4317525906 cites W3202442802 @default.
- W4317525906 cites W4214539264 @default.
- W4317525906 cites W4214620071 @default.
- W4317525906 doi "https://doi.org/10.1007/978-981-19-9297-1_16" @default.
- W4317525906 hasPublicationYear "2022" @default.
- W4317525906 type Work @default.
- W4317525906 citedByCount "0" @default.
- W4317525906 crossrefType "book-chapter" @default.
- W4317525906 hasAuthorship W4317525906A5008844053 @default.
- W4317525906 hasAuthorship W4317525906A5038704690 @default.
- W4317525906 hasAuthorship W4317525906A5059983248 @default.
- W4317525906 hasAuthorship W4317525906A5068061222 @default.
- W4317525906 hasAuthorship W4317525906A5074042241 @default.
- W4317525906 hasConcept C108010975 @default.
- W4317525906 hasConcept C11413529 @default.
- W4317525906 hasConcept C115961682 @default.
- W4317525906 hasConcept C154945302 @default.
- W4317525906 hasConcept C155512373 @default.
- W4317525906 hasConcept C191178318 @default.
- W4317525906 hasConcept C28855332 @default.
- W4317525906 hasConcept C41008148 @default.
- W4317525906 hasConcept C50644808 @default.
- W4317525906 hasConcept C6557445 @default.
- W4317525906 hasConcept C86803240 @default.
- W4317525906 hasConceptScore W4317525906C108010975 @default.
- W4317525906 hasConceptScore W4317525906C11413529 @default.
- W4317525906 hasConceptScore W4317525906C115961682 @default.
- W4317525906 hasConceptScore W4317525906C154945302 @default.
- W4317525906 hasConceptScore W4317525906C155512373 @default.
- W4317525906 hasConceptScore W4317525906C191178318 @default.
- W4317525906 hasConceptScore W4317525906C28855332 @default.
- W4317525906 hasConceptScore W4317525906C41008148 @default.
- W4317525906 hasConceptScore W4317525906C50644808 @default.
- W4317525906 hasConceptScore W4317525906C6557445 @default.
- W4317525906 hasConceptScore W4317525906C86803240 @default.
- W4317525906 hasLocation W43175259061 @default.
- W4317525906 hasOpenAccess W4317525906 @default.
- W4317525906 hasPrimaryLocation W43175259061 @default.
- W4317525906 hasRelatedWork W178936184 @default.
- W4317525906 hasRelatedWork W2354849144 @default.
- W4317525906 hasRelatedWork W2385050764 @default.
- W4317525906 hasRelatedWork W2611186928 @default.
- W4317525906 hasRelatedWork W2750730210 @default.
- W4317525906 hasRelatedWork W2752077245 @default.
- W4317525906 hasRelatedWork W3103243916 @default.
- W4317525906 hasRelatedWork W3173877717 @default.
- W4317525906 hasRelatedWork W4294568054 @default.
- W4317525906 hasRelatedWork W4317525906 @default.
- W4317525906 isParatext "false" @default.
- W4317525906 isRetracted "false" @default.
- W4317525906 workType "book-chapter" @default.