Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285682802> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4285682802 endingPage "563" @default.
- W4285682802 startingPage "553" @default.
- W4285682802 abstract "Convergence of deep neural networks as the depth of the networks tends to infinity is fundamental in building the mathematical foundation for deep learning. In a previous study, we investigated this question for deep networks with the Rectified Linear Unit (ReLU) activation function and with a fixed width. This does not cover the important convolutional neural networks where the widths are increased from layer to layer. For this reason, we first study convergence of general ReLU networks with increased widths and then apply the results obtained to deep convolutional neural networks. It turns out the convergence reduces to convergence of infinite products of matrices with increased sizes, which has not been considered in the literature. We establish sufficient conditions for convergence of such infinite products of matrices. Based on the conditions, we present sufficient conditions for pointwise convergence of general deep ReLU networks with increasing widths, and as well as pointwise convergence of deep ReLU convolutional neural networks." @default.
- W4285682802 created "2022-07-17" @default.
- W4285682802 creator A5023682610 @default.
- W4285682802 creator A5026572582 @default.
- W4285682802 date "2022-09-01" @default.
- W4285682802 modified "2023-10-15" @default.
- W4285682802 title "Convergence of deep convolutional neural networks" @default.
- W4285682802 cites W2021014025 @default.
- W4285682802 cites W2194775991 @default.
- W4285682802 cites W2528305538 @default.
- W4285682802 cites W2550848904 @default.
- W4285682802 cites W2919115771 @default.
- W4285682802 cites W2963172624 @default.
- W4285682802 cites W2963626582 @default.
- W4285682802 cites W2982376398 @default.
- W4285682802 cites W2994632629 @default.
- W4285682802 cites W3031010353 @default.
- W4285682802 cites W3039780279 @default.
- W4285682802 cites W3046650080 @default.
- W4285682802 cites W3048707547 @default.
- W4285682802 cites W3092054443 @default.
- W4285682802 cites W3101996726 @default.
- W4285682802 cites W3121993546 @default.
- W4285682802 cites W3158148831 @default.
- W4285682802 doi "https://doi.org/10.1016/j.neunet.2022.06.031" @default.
- W4285682802 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35839599" @default.
- W4285682802 hasPublicationYear "2022" @default.
- W4285682802 type Work @default.
- W4285682802 citedByCount "10" @default.
- W4285682802 countsByYear W42856828022022 @default.
- W4285682802 countsByYear W42856828022023 @default.
- W4285682802 crossrefType "journal-article" @default.
- W4285682802 hasAuthorship W4285682802A5023682610 @default.
- W4285682802 hasAuthorship W4285682802A5026572582 @default.
- W4285682802 hasBestOaLocation W42856828021 @default.
- W4285682802 hasConcept C108583219 @default.
- W4285682802 hasConcept C111919701 @default.
- W4285682802 hasConcept C11413529 @default.
- W4285682802 hasConcept C134306372 @default.
- W4285682802 hasConcept C14036430 @default.
- W4285682802 hasConcept C154945302 @default.
- W4285682802 hasConcept C162324750 @default.
- W4285682802 hasConcept C199845137 @default.
- W4285682802 hasConcept C27156116 @default.
- W4285682802 hasConcept C2777303404 @default.
- W4285682802 hasConcept C2777984123 @default.
- W4285682802 hasConcept C28826006 @default.
- W4285682802 hasConcept C33923547 @default.
- W4285682802 hasConcept C38365724 @default.
- W4285682802 hasConcept C41008148 @default.
- W4285682802 hasConcept C50522688 @default.
- W4285682802 hasConcept C50644808 @default.
- W4285682802 hasConcept C78458016 @default.
- W4285682802 hasConcept C81363708 @default.
- W4285682802 hasConcept C86803240 @default.
- W4285682802 hasConceptScore W4285682802C108583219 @default.
- W4285682802 hasConceptScore W4285682802C111919701 @default.
- W4285682802 hasConceptScore W4285682802C11413529 @default.
- W4285682802 hasConceptScore W4285682802C134306372 @default.
- W4285682802 hasConceptScore W4285682802C14036430 @default.
- W4285682802 hasConceptScore W4285682802C154945302 @default.
- W4285682802 hasConceptScore W4285682802C162324750 @default.
- W4285682802 hasConceptScore W4285682802C199845137 @default.
- W4285682802 hasConceptScore W4285682802C27156116 @default.
- W4285682802 hasConceptScore W4285682802C2777303404 @default.
- W4285682802 hasConceptScore W4285682802C2777984123 @default.
- W4285682802 hasConceptScore W4285682802C28826006 @default.
- W4285682802 hasConceptScore W4285682802C33923547 @default.
- W4285682802 hasConceptScore W4285682802C38365724 @default.
- W4285682802 hasConceptScore W4285682802C41008148 @default.
- W4285682802 hasConceptScore W4285682802C50522688 @default.
- W4285682802 hasConceptScore W4285682802C50644808 @default.
- W4285682802 hasConceptScore W4285682802C78458016 @default.
- W4285682802 hasConceptScore W4285682802C81363708 @default.
- W4285682802 hasConceptScore W4285682802C86803240 @default.
- W4285682802 hasFunder F4320306076 @default.
- W4285682802 hasFunder F4320321001 @default.
- W4285682802 hasLocation W42856828021 @default.
- W4285682802 hasLocation W42856828022 @default.
- W4285682802 hasLocation W42856828023 @default.
- W4285682802 hasOpenAccess W4285682802 @default.
- W4285682802 hasPrimaryLocation W42856828021 @default.
- W4285682802 hasRelatedWork W2157943005 @default.
- W4285682802 hasRelatedWork W2731899572 @default.
- W4285682802 hasRelatedWork W2999805992 @default.
- W4285682802 hasRelatedWork W3116150086 @default.
- W4285682802 hasRelatedWork W3133861977 @default.
- W4285682802 hasRelatedWork W4200173597 @default.
- W4285682802 hasRelatedWork W4285682802 @default.
- W4285682802 hasRelatedWork W4312417841 @default.
- W4285682802 hasRelatedWork W4312660813 @default.
- W4285682802 hasRelatedWork W4321369474 @default.
- W4285682802 hasVolume "153" @default.
- W4285682802 isParatext "false" @default.
- W4285682802 isRetracted "false" @default.
- W4285682802 workType "article" @default.