Matches in SemOpenAlex for { <https://semopenalex.org/work/W2763224350> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2763224350 abstract "Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of the inter-task relationships to identify the relevant knowledge to transfer. These inter-task relationships are typically estimated based on training data for each task, which is inefficient in lifelong learning settings where the goal is to learn each consecutive task rapidly from as little data as possible. To reduce this burden, we develop a lifelong learning method based on coupled dictionary learning that utilizes high-level task descriptions to model the inter-task relationships. We show that using task descriptors improves the performance of the learned task policies, providing both theoretical justification for the benefit and empirical demonstration of the improvement across a variety of learning problems. Given only the descriptor for a new task, the lifelong learner is also able to accurately predict a model for the new task through zero-shot learning using the coupled dictionary, eliminating the need to gather training data before addressing the task." @default.
- W2763224350 created "2017-10-20" @default.
- W2763224350 creator A5020691490 @default.
- W2763224350 creator A5040786186 @default.
- W2763224350 creator A5063634505 @default.
- W2763224350 date "2017-10-10" @default.
- W2763224350 modified "2023-09-26" @default.
- W2763224350 title "Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer" @default.
- W2763224350 hasPublicationYear "2017" @default.
- W2763224350 type Work @default.
- W2763224350 sameAs 2763224350 @default.
- W2763224350 citedByCount "0" @default.
- W2763224350 crossrefType "posted-content" @default.
- W2763224350 hasAuthorship W2763224350A5020691490 @default.
- W2763224350 hasAuthorship W2763224350A5040786186 @default.
- W2763224350 hasAuthorship W2763224350A5063634505 @default.
- W2763224350 hasConcept C105795698 @default.
- W2763224350 hasConcept C108771440 @default.
- W2763224350 hasConcept C119857082 @default.
- W2763224350 hasConcept C120936955 @default.
- W2763224350 hasConcept C127413603 @default.
- W2763224350 hasConcept C136197465 @default.
- W2763224350 hasConcept C150899416 @default.
- W2763224350 hasConcept C154945302 @default.
- W2763224350 hasConcept C15744967 @default.
- W2763224350 hasConcept C19417346 @default.
- W2763224350 hasConcept C201995342 @default.
- W2763224350 hasConcept C2780451532 @default.
- W2763224350 hasConcept C28006648 @default.
- W2763224350 hasConcept C33923547 @default.
- W2763224350 hasConcept C41008148 @default.
- W2763224350 hasConceptScore W2763224350C105795698 @default.
- W2763224350 hasConceptScore W2763224350C108771440 @default.
- W2763224350 hasConceptScore W2763224350C119857082 @default.
- W2763224350 hasConceptScore W2763224350C120936955 @default.
- W2763224350 hasConceptScore W2763224350C127413603 @default.
- W2763224350 hasConceptScore W2763224350C136197465 @default.
- W2763224350 hasConceptScore W2763224350C150899416 @default.
- W2763224350 hasConceptScore W2763224350C154945302 @default.
- W2763224350 hasConceptScore W2763224350C15744967 @default.
- W2763224350 hasConceptScore W2763224350C19417346 @default.
- W2763224350 hasConceptScore W2763224350C201995342 @default.
- W2763224350 hasConceptScore W2763224350C2780451532 @default.
- W2763224350 hasConceptScore W2763224350C28006648 @default.
- W2763224350 hasConceptScore W2763224350C33923547 @default.
- W2763224350 hasConceptScore W2763224350C41008148 @default.
- W2763224350 hasLocation W27632243501 @default.
- W2763224350 hasOpenAccess W2763224350 @default.
- W2763224350 hasPrimaryLocation W27632243501 @default.
- W2763224350 hasRelatedWork W1522215732 @default.
- W2763224350 hasRelatedWork W1550085722 @default.
- W2763224350 hasRelatedWork W1976105623 @default.
- W2763224350 hasRelatedWork W2578423033 @default.
- W2763224350 hasRelatedWork W2755926663 @default.
- W2763224350 hasRelatedWork W2767835394 @default.
- W2763224350 hasRelatedWork W2903070673 @default.
- W2763224350 hasRelatedWork W2911582157 @default.
- W2763224350 hasRelatedWork W2926719997 @default.
- W2763224350 hasRelatedWork W2993313557 @default.
- W2763224350 hasRelatedWork W2994972936 @default.
- W2763224350 hasRelatedWork W3039645412 @default.
- W2763224350 hasRelatedWork W3094807849 @default.
- W2763224350 hasRelatedWork W3105492668 @default.
- W2763224350 hasRelatedWork W3127033629 @default.
- W2763224350 hasRelatedWork W3176879439 @default.
- W2763224350 hasRelatedWork W3200030979 @default.
- W2763224350 hasRelatedWork W3200043857 @default.
- W2763224350 hasRelatedWork W3208451383 @default.
- W2763224350 hasRelatedWork W3090468760 @default.
- W2763224350 isParatext "false" @default.
- W2763224350 isRetracted "false" @default.
- W2763224350 magId "2763224350" @default.
- W2763224350 workType "article" @default.