Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201947579> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3201947579 abstract "Deep learning has powered recent successes of artificial intelligence (AI). However, the deep neural network, as the basic model of deep learning, has suffered from issues such as local traps and miscalibration. In this paper, we provide a new framework for sparse deep learning, which has the above issues addressed in a coherent way. In particular, we lay down a theoretical foundation for sparse deep learning and propose prior annealing algorithms for learning sparse neural networks. The former has successfully tamed the sparse deep neural network into the framework of statistical modeling, enabling prediction uncertainty correctly quantified. The latter can be asymptotically guaranteed to converge to the global optimum, enabling the validity of the down-stream statistical inference. Numerical result indicates the superiority of the proposed method compared to the existing ones." @default.
- W3201947579 created "2021-10-11" @default.
- W3201947579 creator A5029157131 @default.
- W3201947579 creator A5078166358 @default.
- W3201947579 creator A5085287370 @default.
- W3201947579 date "2021-10-01" @default.
- W3201947579 modified "2023-09-23" @default.
- W3201947579 title "Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration" @default.
- W3201947579 cites W1968261351 @default.
- W3201947579 cites W2017834428 @default.
- W3201947579 cites W2022740958 @default.
- W3201947579 cites W2069026846 @default.
- W3201947579 cites W2076313409 @default.
- W3201947579 cites W2135046866 @default.
- W3201947579 cites W2144193737 @default.
- W3201947579 cites W2154560360 @default.
- W3201947579 cites W2167433878 @default.
- W3201947579 cites W2186210550 @default.
- W3201947579 cites W2194775991 @default.
- W3201947579 cites W2770888898 @default.
- W3201947579 cites W2782893163 @default.
- W3201947579 cites W2794607344 @default.
- W3201947579 cites W2899748887 @default.
- W3201947579 cites W2907886210 @default.
- W3201947579 cites W2956434358 @default.
- W3201947579 cites W2962698540 @default.
- W3201947579 cites W2962732346 @default.
- W3201947579 cites W2963238274 @default.
- W3201947579 cites W2963427613 @default.
- W3201947579 cites W2964059111 @default.
- W3201947579 cites W2964121744 @default.
- W3201947579 cites W2964212410 @default.
- W3201947579 cites W2970443625 @default.
- W3201947579 cites W2971130081 @default.
- W3201947579 cites W2995463996 @default.
- W3201947579 cites W3038042546 @default.
- W3201947579 cites W3100688298 @default.
- W3201947579 cites W3102511045 @default.
- W3201947579 cites W3105108758 @default.
- W3201947579 cites W3118608800 @default.
- W3201947579 cites W3134482315 @default.
- W3201947579 hasPublicationYear "2021" @default.
- W3201947579 type Work @default.
- W3201947579 sameAs 3201947579 @default.
- W3201947579 citedByCount "0" @default.
- W3201947579 crossrefType "posted-content" @default.
- W3201947579 hasAuthorship W3201947579A5029157131 @default.
- W3201947579 hasAuthorship W3201947579A5078166358 @default.
- W3201947579 hasAuthorship W3201947579A5085287370 @default.
- W3201947579 hasBestOaLocation W32019475791 @default.
- W3201947579 hasConcept C105795698 @default.
- W3201947579 hasConcept C108583219 @default.
- W3201947579 hasConcept C119857082 @default.
- W3201947579 hasConcept C126980161 @default.
- W3201947579 hasConcept C134261354 @default.
- W3201947579 hasConcept C154945302 @default.
- W3201947579 hasConcept C2776214188 @default.
- W3201947579 hasConcept C2984842247 @default.
- W3201947579 hasConcept C33923547 @default.
- W3201947579 hasConcept C41008148 @default.
- W3201947579 hasConcept C50644808 @default.
- W3201947579 hasConceptScore W3201947579C105795698 @default.
- W3201947579 hasConceptScore W3201947579C108583219 @default.
- W3201947579 hasConceptScore W3201947579C119857082 @default.
- W3201947579 hasConceptScore W3201947579C126980161 @default.
- W3201947579 hasConceptScore W3201947579C134261354 @default.
- W3201947579 hasConceptScore W3201947579C154945302 @default.
- W3201947579 hasConceptScore W3201947579C2776214188 @default.
- W3201947579 hasConceptScore W3201947579C2984842247 @default.
- W3201947579 hasConceptScore W3201947579C33923547 @default.
- W3201947579 hasConceptScore W3201947579C41008148 @default.
- W3201947579 hasConceptScore W3201947579C50644808 @default.
- W3201947579 hasLocation W32019475791 @default.
- W3201947579 hasOpenAccess W3201947579 @default.
- W3201947579 hasPrimaryLocation W32019475791 @default.
- W3201947579 hasRelatedWork W10534740 @default.
- W3201947579 hasRelatedWork W10699555 @default.
- W3201947579 hasRelatedWork W3370582 @default.
- W3201947579 hasRelatedWork W349990 @default.
- W3201947579 hasRelatedWork W4997104 @default.
- W3201947579 hasRelatedWork W5178400 @default.
- W3201947579 hasRelatedWork W8021486 @default.
- W3201947579 hasRelatedWork W8595301 @default.
- W3201947579 hasRelatedWork W9190101 @default.
- W3201947579 hasRelatedWork W9329549 @default.
- W3201947579 isParatext "false" @default.
- W3201947579 isRetracted "false" @default.
- W3201947579 magId "3201947579" @default.
- W3201947579 workType "article" @default.