Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206170914> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3206170914 abstract "This study proposes a general and unified perspective of convolutional neural networks by exploring the relationship between (deep) convolutional neural networks and finite Volterra convolutions. It provides a novel approach to explain and study the overall characteristics of neural networks without being disturbed by the complex network architectures. Concretely, we examine the basic structures of finite term Volterra convolutions and convolutional neural networks. Our results show that convolutional neural network is an approximation of the finite term Volterra convolution, whose order increases exponentially with the number of layers and kernel size increases exponentially with the strides. With this perspective, the specialized perturbations are directly obtained from the approximated kernels rather than iterative generated adversarial examples. Extensive experiments on synthetic and real-world data sets show the correctness and effectiveness of our results." @default.
- W3206170914 created "2021-10-25" @default.
- W3206170914 creator A5019430201 @default.
- W3206170914 creator A5070961417 @default.
- W3206170914 creator A5083182987 @default.
- W3206170914 creator A5090101808 @default.
- W3206170914 date "2021-10-19" @default.
- W3206170914 modified "2023-09-23" @default.
- W3206170914 title "Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution" @default.
- W3206170914 cites W1615672776 @default.
- W3206170914 cites W1945616565 @default.
- W3206170914 cites W1970763581 @default.
- W3206170914 cites W1986326495 @default.
- W3206170914 cites W2042873906 @default.
- W3206170914 cites W2050834445 @default.
- W3206170914 cites W2097117768 @default.
- W3206170914 cites W2103496339 @default.
- W3206170914 cites W2112796928 @default.
- W3206170914 cites W2117561644 @default.
- W3206170914 cites W2141200610 @default.
- W3206170914 cites W2160068178 @default.
- W3206170914 cites W2194775991 @default.
- W3206170914 cites W2600297185 @default.
- W3206170914 cites W2610857016 @default.
- W3206170914 cites W2940107683 @default.
- W3206170914 cites W2949117887 @default.
- W3206170914 cites W2963840672 @default.
- W3206170914 cites W2964153729 @default.
- W3206170914 cites W3018252856 @default.
- W3206170914 cites W3101985406 @default.
- W3206170914 cites W3136879969 @default.
- W3206170914 cites W3146803896 @default.
- W3206170914 cites W3157286395 @default.
- W3206170914 cites W3205586852 @default.
- W3206170914 hasPublicationYear "2021" @default.
- W3206170914 type Work @default.
- W3206170914 sameAs 3206170914 @default.
- W3206170914 citedByCount "0" @default.
- W3206170914 crossrefType "posted-content" @default.
- W3206170914 hasAuthorship W3206170914A5019430201 @default.
- W3206170914 hasAuthorship W3206170914A5070961417 @default.
- W3206170914 hasAuthorship W3206170914A5083182987 @default.
- W3206170914 hasAuthorship W3206170914A5090101808 @default.
- W3206170914 hasBestOaLocation W32061709141 @default.
- W3206170914 hasConcept C108583219 @default.
- W3206170914 hasConcept C11413529 @default.
- W3206170914 hasConcept C118615104 @default.
- W3206170914 hasConcept C126255220 @default.
- W3206170914 hasConcept C12713177 @default.
- W3206170914 hasConcept C154945302 @default.
- W3206170914 hasConcept C28826006 @default.
- W3206170914 hasConcept C33923547 @default.
- W3206170914 hasConcept C41008148 @default.
- W3206170914 hasConcept C45347329 @default.
- W3206170914 hasConcept C50644808 @default.
- W3206170914 hasConcept C55439883 @default.
- W3206170914 hasConcept C74193536 @default.
- W3206170914 hasConcept C81363708 @default.
- W3206170914 hasConceptScore W3206170914C108583219 @default.
- W3206170914 hasConceptScore W3206170914C11413529 @default.
- W3206170914 hasConceptScore W3206170914C118615104 @default.
- W3206170914 hasConceptScore W3206170914C126255220 @default.
- W3206170914 hasConceptScore W3206170914C12713177 @default.
- W3206170914 hasConceptScore W3206170914C154945302 @default.
- W3206170914 hasConceptScore W3206170914C28826006 @default.
- W3206170914 hasConceptScore W3206170914C33923547 @default.
- W3206170914 hasConceptScore W3206170914C41008148 @default.
- W3206170914 hasConceptScore W3206170914C45347329 @default.
- W3206170914 hasConceptScore W3206170914C50644808 @default.
- W3206170914 hasConceptScore W3206170914C55439883 @default.
- W3206170914 hasConceptScore W3206170914C74193536 @default.
- W3206170914 hasConceptScore W3206170914C81363708 @default.
- W3206170914 hasLocation W32061709141 @default.
- W3206170914 hasOpenAccess W3206170914 @default.
- W3206170914 hasPrimaryLocation W32061709141 @default.
- W3206170914 hasRelatedWork W3781714 @default.
- W3206170914 hasRelatedWork W4136762 @default.
- W3206170914 hasRelatedWork W4827971 @default.
- W3206170914 hasRelatedWork W5765193 @default.
- W3206170914 hasRelatedWork W7432053 @default.
- W3206170914 hasRelatedWork W819137 @default.
- W3206170914 hasRelatedWork W8203773 @default.
- W3206170914 hasRelatedWork W9190101 @default.
- W3206170914 hasRelatedWork W9554121 @default.
- W3206170914 hasRelatedWork W14377099 @default.
- W3206170914 isParatext "false" @default.
- W3206170914 isRetracted "false" @default.
- W3206170914 magId "3206170914" @default.
- W3206170914 workType "article" @default.