FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952661520> ?p ?o ?g. }

• W2952661520 abstract "The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation problems than shallow, one-hidden layer architectures. The paper announces new results for a non-smooth activation function - the ReLU function - used in present-day neural networks, as well as for the Gaussian networks. We propose a new definition of relative dimension to encapsulate different notions of sparsity of a function class that can possibly be exploited by deep networks but not by shallow ones to drastically reduce the complexity required for approximation and learning." @default.
• W2952661520 created "2019-06-27" @default.
• W2952661520 creator A5001833084 @default.
• W2952661520 creator A5056481363 @default.
• W2952661520 date "2016-08-10" @default.
• W2952661520 modified "2023-09-27" @default.
• W2952661520 title "Deep vs. shallow networks : An approximation theory perspective" @default.
• W2952661520 cites W122942132 @default.
• W2952661520 cites W137098816 @default.
• W2952661520 cites W1489213177 @default.
• W2952661520 cites W1990261069 @default.
• W2952661520 cites W2014992345 @default.
• W2952661520 cites W2017290750 @default.
• W2952661520 cites W2021676252 @default.
• W2952661520 cites W2077887717 @default.
• W2952661520 cites W2079224763 @default.
• W2952661520 cites W2085481869 @default.
• W2952661520 cites W2087948458 @default.
• W2952661520 cites W2101926813 @default.
• W2952661520 cites W2118818460 @default.
• W2952661520 cites W2149194912 @default.
• W2952661520 cites W2194775991 @default.
• W2952661520 cites W2206396100 @default.
• W2952661520 cites W2208555118 @default.
• W2952661520 cites W2253400648 @default.
• W2952661520 cites W2495042831 @default.
• W2952661520 cites W2535756153 @default.
• W2952661520 cites W2919115771 @default.
• W2952661520 cites W2963072276 @default.
• W2952661520 hasPublicationYear "2016" @default.
• W2952661520 type Work @default.
• W2952661520 sameAs 2952661520 @default.
• W2952661520 citedByCount "7" @default.
• W2952661520 countsByYear W29526615202016 @default.
• W2952661520 countsByYear W29526615202017 @default.
• W2952661520 countsByYear W29526615202018 @default.
• W2952661520 countsByYear W29526615202019 @default.
• W2952661520 crossrefType "posted-content" @default.
• W2952661520 hasAuthorship W2952661520A5001833084 @default.
• W2952661520 hasAuthorship W2952661520A5056481363 @default.
• W2952661520 hasConcept C108583219 @default.
• W2952661520 hasConcept C121332964 @default.
• W2952661520 hasConcept C12713177 @default.
• W2952661520 hasConcept C14036430 @default.
• W2952661520 hasConcept C154945302 @default.
• W2952661520 hasConcept C163716315 @default.
• W2952661520 hasConcept C202444582 @default.
• W2952661520 hasConcept C2777212361 @default.
• W2952661520 hasConcept C2984842247 @default.
• W2952661520 hasConcept C33676613 @default.
• W2952661520 hasConcept C33923547 @default.
• W2952661520 hasConcept C41008148 @default.
• W2952661520 hasConcept C50644808 @default.
• W2952661520 hasConcept C62520636 @default.
• W2952661520 hasConcept C78458016 @default.
• W2952661520 hasConcept C80444323 @default.
• W2952661520 hasConcept C81363708 @default.
• W2952661520 hasConcept C86803240 @default.
• W2952661520 hasConcept C91873725 @default.
• W2952661520 hasConceptScore W2952661520C108583219 @default.
• W2952661520 hasConceptScore W2952661520C121332964 @default.
• W2952661520 hasConceptScore W2952661520C12713177 @default.
• W2952661520 hasConceptScore W2952661520C14036430 @default.
• W2952661520 hasConceptScore W2952661520C154945302 @default.
• W2952661520 hasConceptScore W2952661520C163716315 @default.
• W2952661520 hasConceptScore W2952661520C202444582 @default.
• W2952661520 hasConceptScore W2952661520C2777212361 @default.
• W2952661520 hasConceptScore W2952661520C2984842247 @default.
• W2952661520 hasConceptScore W2952661520C33676613 @default.
• W2952661520 hasConceptScore W2952661520C33923547 @default.
• W2952661520 hasConceptScore W2952661520C41008148 @default.
• W2952661520 hasConceptScore W2952661520C50644808 @default.
• W2952661520 hasConceptScore W2952661520C62520636 @default.
• W2952661520 hasConceptScore W2952661520C78458016 @default.
• W2952661520 hasConceptScore W2952661520C80444323 @default.
• W2952661520 hasConceptScore W2952661520C81363708 @default.
• W2952661520 hasConceptScore W2952661520C86803240 @default.
• W2952661520 hasConceptScore W2952661520C91873725 @default.
• W2952661520 hasLocation W29526615201 @default.
• W2952661520 hasOpenAccess W2952661520 @default.
• W2952661520 hasPrimaryLocation W29526615201 @default.
• W2952661520 hasRelatedWork W1763914265 @default.
• W2952661520 hasRelatedWork W2141473882 @default.
• W2952661520 hasRelatedWork W2212676342 @default.
• W2952661520 hasRelatedWork W2513671774 @default.
• W2952661520 hasRelatedWork W2528305538 @default.
• W2952661520 hasRelatedWork W2749030024 @default.
• W2952661520 hasRelatedWork W2749945115 @default.
• W2952661520 hasRelatedWork W2899748887 @default.
• W2952661520 hasRelatedWork W2931679349 @default.
• W2952661520 hasRelatedWork W2943191253 @default.
• W2952661520 hasRelatedWork W2944820194 @default.
• W2952661520 hasRelatedWork W2963504252 @default.
• W2952661520 hasRelatedWork W2963545397 @default.
• W2952661520 hasRelatedWork W2964003140 @default.
• W2952661520 hasRelatedWork W2977834236 @default.
• W2952661520 hasRelatedWork W2982876570 @default.
• W2952661520 hasRelatedWork W3002335888 @default.
• W2952661520 hasRelatedWork W3040743533 @default.
• W2952661520 hasRelatedWork W3126988966 @default.

• next