FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951134251> ?p ?o ?g. }

• W2951134251 abstract "Nowadays, the number of layers and of neurons in each layer of a deep network are typically set manually. While very deep and wide networks have proven effective in general, they come at a high memory and computation cost, thus making them impractical for constrained platforms. These networks, however, are known to have many redundant parameters, and could thus, in principle, be replaced by more compact architectures. In this paper, we introduce an approach to automatically determining the number of neurons in each layer of a deep network during learning. To this end, we propose to make use of structured sparsity during learning. More precisely, we use a group sparsity regularizer on the parameters of the network, where each group is defined to act on a single neuron. Starting from an overcomplete network, we show that our approach can reduce the number of parameters by up to 80% while retaining or even improving the network accuracy." @default.
• W2951134251 created "2019-06-27" @default.
• W2951134251 creator A5020898778 @default.
• W2951134251 creator A5049300388 @default.
• W2951134251 date "2016-11-19" @default.
• W2951134251 modified "2023-10-18" @default.
• W2951134251 title "Learning the Number of Neurons in Deep Networks." @default.
• W2951134251 cites W1570197553 @default.
• W2951134251 cites W1686810756 @default.
• W2951134251 cites W1724438581 @default.
• W2951134251 cites W1821462560 @default.
• W2951134251 cites W1935978687 @default.
• W2951134251 cites W1987371344 @default.
• W2951134251 cites W2002847526 @default.
• W2951134251 cites W2042481239 @default.
• W2951134251 cites W2114766824 @default.
• W2951134251 cites W2117539524 @default.
• W2951134251 cites W2128882956 @default.
• W2951134251 cites W2134273960 @default.
• W2951134251 cites W2138019504 @default.
• W2951134251 cites W2144513243 @default.
• W2951134251 cites W2145085734 @default.
• W2951134251 cites W2156150815 @default.
• W2951134251 cites W2162488714 @default.
• W2951134251 cites W2164359548 @default.
• W2951134251 cites W2167215970 @default.
• W2951134251 cites W2422848620 @default.
• W2951134251 cites W2520760693 @default.
• W2951134251 cites W2913535645 @default.
• W2951134251 cites W2949560654 @default.
• W2951134251 cites W2949650786 @default.
• W2951134251 cites W2950621961 @default.
• W2951134251 cites W2950967261 @default.
• W2951134251 cites W2951603627 @default.
• W2951134251 cites W2952271367 @default.
• W2951134251 cites W2952899695 @default.
• W2951134251 cites W2953071172 @default.
• W2951134251 cites W2964118293 @default.
• W2951134251 cites W3037950864 @default.
• W2951134251 cites W368469426 @default.
• W2951134251 cites W70975097 @default.
• W2951134251 cites W753012316 @default.
• W2951134251 hasPublicationYear "2016" @default.
• W2951134251 type Work @default.
• W2951134251 sameAs 2951134251 @default.
• W2951134251 citedByCount "56" @default.
• W2951134251 countsByYear W29511342512016 @default.
• W2951134251 countsByYear W29511342512017 @default.
• W2951134251 countsByYear W29511342512018 @default.
• W2951134251 countsByYear W29511342512019 @default.
• W2951134251 countsByYear W29511342512020 @default.
• W2951134251 countsByYear W29511342512021 @default.
• W2951134251 crossrefType "posted-content" @default.
• W2951134251 hasAuthorship W2951134251A5020898778 @default.
• W2951134251 hasAuthorship W2951134251A5049300388 @default.
• W2951134251 hasConcept C108583219 @default.
• W2951134251 hasConcept C11413529 @default.
• W2951134251 hasConcept C154945302 @default.
• W2951134251 hasConcept C177264268 @default.
• W2951134251 hasConcept C178790620 @default.
• W2951134251 hasConcept C185592680 @default.
• W2951134251 hasConcept C199360897 @default.
• W2951134251 hasConcept C2779227376 @default.
• W2951134251 hasConcept C41008148 @default.
• W2951134251 hasConcept C45374587 @default.
• W2951134251 hasConceptScore W2951134251C108583219 @default.
• W2951134251 hasConceptScore W2951134251C11413529 @default.
• W2951134251 hasConceptScore W2951134251C154945302 @default.
• W2951134251 hasConceptScore W2951134251C177264268 @default.
• W2951134251 hasConceptScore W2951134251C178790620 @default.
• W2951134251 hasConceptScore W2951134251C185592680 @default.
• W2951134251 hasConceptScore W2951134251C199360897 @default.
• W2951134251 hasConceptScore W2951134251C2779227376 @default.
• W2951134251 hasConceptScore W2951134251C41008148 @default.
• W2951134251 hasConceptScore W2951134251C45374587 @default.
• W2951134251 hasLocation W29511342511 @default.
• W2951134251 hasOpenAccess W2951134251 @default.
• W2951134251 hasPrimaryLocation W29511342511 @default.
• W2951134251 hasRelatedWork W1686810756 @default.
• W2951134251 hasRelatedWork W1821462560 @default.
• W2951134251 hasRelatedWork W2097117768 @default.
• W2951134251 hasRelatedWork W2108598243 @default.
• W2951134251 hasRelatedWork W2112796928 @default.
• W2951134251 hasRelatedWork W2114766824 @default.
• W2951134251 hasRelatedWork W2117539524 @default.
• W2951134251 hasRelatedWork W2125389748 @default.
• W2951134251 hasRelatedWork W2163605009 @default.
• W2951134251 hasRelatedWork W2194775991 @default.
• W2951134251 hasRelatedWork W2495425901 @default.
• W2951134251 hasRelatedWork W2513419314 @default.
• W2951134251 hasRelatedWork W2515385951 @default.
• W2951134251 hasRelatedWork W2520760693 @default.
• W2951134251 hasRelatedWork W2612445135 @default.
• W2951134251 hasRelatedWork W2737121650 @default.
• W2951134251 hasRelatedWork W2949117887 @default.
• W2951134251 hasRelatedWork W2963674932 @default.
• W2951134251 hasRelatedWork W2964299589 @default.
• W2951134251 hasRelatedWork W3118608800 @default.
• W2951134251 isParatext "false" @default.
• W2951134251 isRetracted "false" @default.

• next