Matches in SemOpenAlex for { <https://semopenalex.org/work/W3101926816> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3101926816 endingPage "2431" @default.
- W3101926816 startingPage "2420" @default.
- W3101926816 abstract "One of the most important steps toward interpretability and explainability of neural network models is feature selection, which aims to identify the subset of relevant features. Theoretical results in the field have mostly focused on the prediction aspect of the problem with virtually no work on feature selection consistency for deep neural networks due to the model's severe nonlinearity and unidentifiability. This lack of theoretical foundation casts doubt on the applicability of deep learning to contexts where correct interpretations of the features play a central role. In this work, we investigate the problem of feature selection for analytic deep networks. We prove that for a wide class of networks, including deep feed-forward neural networks, convolutional neural networks, and a major sub-class of residual neural networks, the Adaptive Group Lasso selection procedure with Group Lasso as the base estimator is selection-consistent. The work provides further evidence that Group Lasso might be inefficient for feature selection with neural networks and advocates the use of Adaptive Group Lasso over the popular Group Lasso." @default.
- W3101926816 created "2020-11-23" @default.
- W3101926816 creator A5018509696 @default.
- W3101926816 creator A5025885529 @default.
- W3101926816 date "2020-01-01" @default.
- W3101926816 modified "2023-10-18" @default.
- W3101926816 title "Consistent feature selection for analytic deep neural networks" @default.
- W3101926816 hasPublicationYear "2020" @default.
- W3101926816 type Work @default.
- W3101926816 sameAs 3101926816 @default.
- W3101926816 citedByCount "3" @default.
- W3101926816 countsByYear W31019268162021 @default.
- W3101926816 crossrefType "proceedings-article" @default.
- W3101926816 hasAuthorship W3101926816A5018509696 @default.
- W3101926816 hasAuthorship W3101926816A5025885529 @default.
- W3101926816 hasConcept C105795698 @default.
- W3101926816 hasConcept C108583219 @default.
- W3101926816 hasConcept C119857082 @default.
- W3101926816 hasConcept C136764020 @default.
- W3101926816 hasConcept C138885662 @default.
- W3101926816 hasConcept C148483581 @default.
- W3101926816 hasConcept C154945302 @default.
- W3101926816 hasConcept C185429906 @default.
- W3101926816 hasConcept C2776401178 @default.
- W3101926816 hasConcept C2776436953 @default.
- W3101926816 hasConcept C2781067378 @default.
- W3101926816 hasConcept C33923547 @default.
- W3101926816 hasConcept C37616216 @default.
- W3101926816 hasConcept C41008148 @default.
- W3101926816 hasConcept C41895202 @default.
- W3101926816 hasConcept C50644808 @default.
- W3101926816 hasConcept C81363708 @default.
- W3101926816 hasConcept C81917197 @default.
- W3101926816 hasConceptScore W3101926816C105795698 @default.
- W3101926816 hasConceptScore W3101926816C108583219 @default.
- W3101926816 hasConceptScore W3101926816C119857082 @default.
- W3101926816 hasConceptScore W3101926816C136764020 @default.
- W3101926816 hasConceptScore W3101926816C138885662 @default.
- W3101926816 hasConceptScore W3101926816C148483581 @default.
- W3101926816 hasConceptScore W3101926816C154945302 @default.
- W3101926816 hasConceptScore W3101926816C185429906 @default.
- W3101926816 hasConceptScore W3101926816C2776401178 @default.
- W3101926816 hasConceptScore W3101926816C2776436953 @default.
- W3101926816 hasConceptScore W3101926816C2781067378 @default.
- W3101926816 hasConceptScore W3101926816C33923547 @default.
- W3101926816 hasConceptScore W3101926816C37616216 @default.
- W3101926816 hasConceptScore W3101926816C41008148 @default.
- W3101926816 hasConceptScore W3101926816C41895202 @default.
- W3101926816 hasConceptScore W3101926816C50644808 @default.
- W3101926816 hasConceptScore W3101926816C81363708 @default.
- W3101926816 hasConceptScore W3101926816C81917197 @default.
- W3101926816 hasLocation W31019268161 @default.
- W3101926816 hasOpenAccess W3101926816 @default.
- W3101926816 hasPrimaryLocation W31019268161 @default.
- W3101926816 hasRelatedWork W2787881900 @default.
- W3101926816 hasRelatedWork W2807679857 @default.
- W3101926816 hasRelatedWork W2894867725 @default.
- W3101926816 hasRelatedWork W2945205529 @default.
- W3101926816 hasRelatedWork W2954040262 @default.
- W3101926816 hasRelatedWork W2998416827 @default.
- W3101926816 hasRelatedWork W3000120900 @default.
- W3101926816 hasRelatedWork W3003921671 @default.
- W3101926816 hasRelatedWork W3023570597 @default.
- W3101926816 hasRelatedWork W3030137591 @default.
- W3101926816 hasRelatedWork W3034802003 @default.
- W3101926816 hasRelatedWork W3092726106 @default.
- W3101926816 hasRelatedWork W3129620938 @default.
- W3101926816 hasRelatedWork W3135482464 @default.
- W3101926816 hasRelatedWork W3156792465 @default.
- W3101926816 hasRelatedWork W3172466651 @default.
- W3101926816 hasRelatedWork W3173999938 @default.
- W3101926816 hasRelatedWork W3181663402 @default.
- W3101926816 hasRelatedWork W3204364042 @default.
- W3101926816 hasRelatedWork W3096979466 @default.
- W3101926816 hasVolume "33" @default.
- W3101926816 isParatext "false" @default.
- W3101926816 isRetracted "false" @default.
- W3101926816 magId "3101926816" @default.
- W3101926816 workType "article" @default.