Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310253114> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4310253114 endingPage "125" @default.
- W4310253114 startingPage "93" @default.
- W4310253114 abstract "Deep convolutional neural networks (DCNNs) have achieved great empirical success in many fields such as natural language processing, computer vision, and pattern recognition. But there still lacks theoretical understanding of the flexibility and adaptivity of DCNNs in various learning tasks, and the power of DCNNs at feature extraction. We propose a generic DCNN structure consisting of two groups of convolutional layers associated with two downsampling operators, and a fully connected layer, which is determined only by three structural parameters. Our generic DCNNs are capable of extracting various features including not only polynomial features but also general smooth features. We also show that the curse of dimensionality can be circumvented by our DCNNs for target functions of the compositional form with (symmetric) polynomial features, spatially sparse smooth features, and interaction features. These demonstrate the expressive power of our DCNN structure, while the model selection can be relaxed comparing with other deep neural networks since there are only three hyperparameters controlling the architecture to tune." @default.
- W4310253114 created "2022-11-30" @default.
- W4310253114 creator A5004291695 @default.
- W4310253114 creator A5006802589 @default.
- W4310253114 creator A5021481651 @default.
- W4310253114 date "2022-11-26" @default.
- W4310253114 modified "2023-10-05" @default.
- W4310253114 title "Approximating functions with multi-features by deep convolutional neural networks" @default.
- W4310253114 cites W1984137599 @default.
- W4310253114 cites W1991818747 @default.
- W4310253114 cites W2006240266 @default.
- W4310253114 cites W2051968241 @default.
- W4310253114 cites W2053521124 @default.
- W4310253114 cites W2103496339 @default.
- W4310253114 cites W2136922672 @default.
- W4310253114 cites W2137983211 @default.
- W4310253114 cites W2166116275 @default.
- W4310253114 cites W2261689926 @default.
- W4310253114 cites W2513671774 @default.
- W4310253114 cites W2528305538 @default.
- W4310253114 cites W2559431973 @default.
- W4310253114 cites W2766447205 @default.
- W4310253114 cites W2789237874 @default.
- W4310253114 cites W2803636134 @default.
- W4310253114 cites W2886881190 @default.
- W4310253114 cites W2946302218 @default.
- W4310253114 cites W2962957157 @default.
- W4310253114 cites W2963482148 @default.
- W4310253114 cites W2963626582 @default.
- W4310253114 cites W2982376398 @default.
- W4310253114 cites W3002335888 @default.
- W4310253114 cites W3014385693 @default.
- W4310253114 cites W3047620219 @default.
- W4310253114 cites W3202429688 @default.
- W4310253114 cites W4226270014 @default.
- W4310253114 cites W4242686374 @default.
- W4310253114 cites W4245558064 @default.
- W4310253114 cites W4285305182 @default.
- W4310253114 doi "https://doi.org/10.1142/s0219530522400085" @default.
- W4310253114 hasPublicationYear "2022" @default.
- W4310253114 type Work @default.
- W4310253114 citedByCount "9" @default.
- W4310253114 countsByYear W43102531142023 @default.
- W4310253114 crossrefType "journal-article" @default.
- W4310253114 hasAuthorship W4310253114A5004291695 @default.
- W4310253114 hasAuthorship W4310253114A5006802589 @default.
- W4310253114 hasAuthorship W4310253114A5021481651 @default.
- W4310253114 hasConcept C108583219 @default.
- W4310253114 hasConcept C110384440 @default.
- W4310253114 hasConcept C111030470 @default.
- W4310253114 hasConcept C115961682 @default.
- W4310253114 hasConcept C134306372 @default.
- W4310253114 hasConcept C138885662 @default.
- W4310253114 hasConcept C153180895 @default.
- W4310253114 hasConcept C154945302 @default.
- W4310253114 hasConcept C2776401178 @default.
- W4310253114 hasConcept C33923547 @default.
- W4310253114 hasConcept C41008148 @default.
- W4310253114 hasConcept C41895202 @default.
- W4310253114 hasConcept C52622490 @default.
- W4310253114 hasConcept C81363708 @default.
- W4310253114 hasConcept C90119067 @default.
- W4310253114 hasConceptScore W4310253114C108583219 @default.
- W4310253114 hasConceptScore W4310253114C110384440 @default.
- W4310253114 hasConceptScore W4310253114C111030470 @default.
- W4310253114 hasConceptScore W4310253114C115961682 @default.
- W4310253114 hasConceptScore W4310253114C134306372 @default.
- W4310253114 hasConceptScore W4310253114C138885662 @default.
- W4310253114 hasConceptScore W4310253114C153180895 @default.
- W4310253114 hasConceptScore W4310253114C154945302 @default.
- W4310253114 hasConceptScore W4310253114C2776401178 @default.
- W4310253114 hasConceptScore W4310253114C33923547 @default.
- W4310253114 hasConceptScore W4310253114C41008148 @default.
- W4310253114 hasConceptScore W4310253114C41895202 @default.
- W4310253114 hasConceptScore W4310253114C52622490 @default.
- W4310253114 hasConceptScore W4310253114C81363708 @default.
- W4310253114 hasConceptScore W4310253114C90119067 @default.
- W4310253114 hasFunder F4320321001 @default.
- W4310253114 hasIssue "01" @default.
- W4310253114 hasLocation W43102531141 @default.
- W4310253114 hasOpenAccess W4310253114 @default.
- W4310253114 hasPrimaryLocation W43102531141 @default.
- W4310253114 hasRelatedWork W2279398222 @default.
- W4310253114 hasRelatedWork W2546942002 @default.
- W4310253114 hasRelatedWork W2731899572 @default.
- W4310253114 hasRelatedWork W3091976719 @default.
- W4310253114 hasRelatedWork W3133861977 @default.
- W4310253114 hasRelatedWork W3156786002 @default.
- W4310253114 hasRelatedWork W4299822940 @default.
- W4310253114 hasRelatedWork W4312417841 @default.
- W4310253114 hasRelatedWork W4321369474 @default.
- W4310253114 hasRelatedWork W4366492315 @default.
- W4310253114 hasVolume "21" @default.
- W4310253114 isParatext "false" @default.
- W4310253114 isRetracted "false" @default.
- W4310253114 workType "article" @default.