FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2794356495> ?p ?o ?g. }

• W2794356495 abstract "Deep multitask learning boosts performance by sharing learned structure across related tasks. This paper adapts ideas from deep multitask learning to the setting where only a single task is available. The method is formalized as pseudo-task augmentation, in which models are trained with multiple decoders for each task. Pseudo-tasks simulate the effect of training towards closely-related tasks drawn from the same universe. In a suite of experiments, pseudo-task augmentation is shown to improve performance on single-task learning problems. When combined with multitask learning, further improvements are achieved, including state-of-the-art performance on the CelebA dataset, showing that pseudo-task augmentation and multitask learning have complementary value. All in all, pseudo-task augmentation is a broadly applicable and efficient way to boost performance in deep learning systems." @default.
• W2794356495 created "2018-03-29" @default.
• W2794356495 creator A5020441009 @default.
• W2794356495 creator A5020821744 @default.
• W2794356495 date "2018-03-11" @default.
• W2794356495 modified "2023-09-27" @default.
• W2794356495 title "Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back" @default.
• W2794356495 cites W1499332833 @default.
• W2794356495 cites W1868018859 @default.
• W2794356495 cites W1896424170 @default.
• W2794356495 cites W2025198378 @default.
• W2794356495 cites W2065180801 @default.
• W2794356495 cites W2094035326 @default.
• W2794356495 cites W2095705004 @default.
• W2794356495 cites W2106411961 @default.
• W2794356495 cites W2108723060 @default.
• W2794356495 cites W2117130368 @default.
• W2794356495 cites W2117539524 @default.
• W2794356495 cites W2136836265 @default.
• W2794356495 cites W2143104527 @default.
• W2794356495 cites W2165347833 @default.
• W2794356495 cites W2186054958 @default.
• W2794356495 cites W2251743902 @default.
• W2794356495 cites W2256348663 @default.
• W2794356495 cites W2274287116 @default.
• W2794356495 cites W2290180618 @default.
• W2794356495 cites W2311095070 @default.
• W2794356495 cites W2339391301 @default.
• W2794356495 cites W2407277018 @default.
• W2794356495 cites W2407793339 @default.
• W2794356495 cites W2549401308 @default.
• W2794356495 cites W2553303224 @default.
• W2794356495 cites W2556468274 @default.
• W2794356495 cites W2583761661 @default.
• W2794356495 cites W2593744649 @default.
• W2794356495 cites W2605124728 @default.
• W2794356495 cites W2607361225 @default.
• W2794356495 cites W2616957565 @default.
• W2794356495 cites W2624871570 @default.
• W2794356495 cites W2626792426 @default.
• W2794356495 cites W2735995851 @default.
• W2794356495 cites W2740711318 @default.
• W2794356495 cites W2767286446 @default.
• W2794356495 cites W2949201716 @default.
• W2794356495 cites W2949886837 @default.
• W2794356495 cites W2950182411 @default.
• W2794356495 cites W2950872548 @default.
• W2794356495 cites W2963268748 @default.
• W2794356495 cites W2963504252 @default.
• W2794356495 cites W2963628712 @default.
• W2794356495 cites W2963704251 @default.
• W2794356495 cites W2963842982 @default.
• W2794356495 cites W2964056935 @default.
• W2794356495 cites W2964121744 @default.
• W2794356495 cites W3038130178 @default.
• W2794356495 cites W2770298516 @default.
• W2794356495 hasPublicationYear "2018" @default.
• W2794356495 type Work @default.
• W2794356495 sameAs 2794356495 @default.
• W2794356495 citedByCount "3" @default.
• W2794356495 countsByYear W27943564952018 @default.
• W2794356495 countsByYear W27943564952020 @default.
• W2794356495 crossrefType "posted-content" @default.
• W2794356495 hasAuthorship W2794356495A5020441009 @default.
• W2794356495 hasAuthorship W2794356495A5020821744 @default.
• W2794356495 hasConcept C108583219 @default.
• W2794356495 hasConcept C119857082 @default.
• W2794356495 hasConcept C127413603 @default.
• W2794356495 hasConcept C154945302 @default.
• W2794356495 hasConcept C166957645 @default.
• W2794356495 hasConcept C201995342 @default.
• W2794356495 hasConcept C2780451532 @default.
• W2794356495 hasConcept C28006648 @default.
• W2794356495 hasConcept C41008148 @default.
• W2794356495 hasConcept C79581498 @default.
• W2794356495 hasConcept C95457728 @default.
• W2794356495 hasConceptScore W2794356495C108583219 @default.
• W2794356495 hasConceptScore W2794356495C119857082 @default.
• W2794356495 hasConceptScore W2794356495C127413603 @default.
• W2794356495 hasConceptScore W2794356495C154945302 @default.
• W2794356495 hasConceptScore W2794356495C166957645 @default.
• W2794356495 hasConceptScore W2794356495C201995342 @default.
• W2794356495 hasConceptScore W2794356495C2780451532 @default.
• W2794356495 hasConceptScore W2794356495C28006648 @default.
• W2794356495 hasConceptScore W2794356495C41008148 @default.
• W2794356495 hasConceptScore W2794356495C79581498 @default.
• W2794356495 hasConceptScore W2794356495C95457728 @default.
• W2794356495 hasLocation W27943564951 @default.
• W2794356495 hasOpenAccess W2794356495 @default.
• W2794356495 hasPrimaryLocation W27943564951 @default.
• W2794356495 hasRelatedWork W104574262 @default.
• W2794356495 hasRelatedWork W1192033990 @default.
• W2794356495 hasRelatedWork W1585952056 @default.
• W2794356495 hasRelatedWork W2129427976 @default.
• W2794356495 hasRelatedWork W2181724605 @default.
• W2794356495 hasRelatedWork W2590567779 @default.
• W2794356495 hasRelatedWork W2680401079 @default.
• W2794356495 hasRelatedWork W2787824708 @default.
• W2794356495 hasRelatedWork W2922338626 @default.
• W2794356495 hasRelatedWork W2952195321 @default.

• next