Matches in SemOpenAlex for { <https://semopenalex.org/work/W3014201747> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3014201747 endingPage "704" @default.
- W3014201747 startingPage "673" @default.
- W3014201747 abstract "Knowledge transfer between tasks can improve the performance of learned models, but requires an accurate estimate of 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 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.
- W3014201747 created "2020-04-10" @default.
- W3014201747 creator A5020691490 @default.
- W3014201747 creator A5040786186 @default.
- W3014201747 creator A5063634505 @default.
- W3014201747 date "2020-03-29" @default.
- W3014201747 modified "2023-10-10" @default.
- W3014201747 title "Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer" @default.
- W3014201747 doi "https://doi.org/10.1613/jair.1.11304" @default.
- W3014201747 hasPublicationYear "2020" @default.
- W3014201747 type Work @default.
- W3014201747 sameAs 3014201747 @default.
- W3014201747 citedByCount "7" @default.
- W3014201747 countsByYear W30142017472021 @default.
- W3014201747 countsByYear W30142017472022 @default.
- W3014201747 countsByYear W30142017472023 @default.
- W3014201747 crossrefType "journal-article" @default.
- W3014201747 hasAuthorship W3014201747A5020691490 @default.
- W3014201747 hasAuthorship W3014201747A5040786186 @default.
- W3014201747 hasAuthorship W3014201747A5063634505 @default.
- W3014201747 hasBestOaLocation W30142017471 @default.
- W3014201747 hasConcept C105795698 @default.
- W3014201747 hasConcept C108771440 @default.
- W3014201747 hasConcept C119857082 @default.
- W3014201747 hasConcept C120936955 @default.
- W3014201747 hasConcept C127413603 @default.
- W3014201747 hasConcept C136197465 @default.
- W3014201747 hasConcept C150899416 @default.
- W3014201747 hasConcept C154945302 @default.
- W3014201747 hasConcept C15744967 @default.
- W3014201747 hasConcept C175154964 @default.
- W3014201747 hasConcept C19417346 @default.
- W3014201747 hasConcept C201995342 @default.
- W3014201747 hasConcept C2780451532 @default.
- W3014201747 hasConcept C28006648 @default.
- W3014201747 hasConcept C33923547 @default.
- W3014201747 hasConcept C41008148 @default.
- W3014201747 hasConceptScore W3014201747C105795698 @default.
- W3014201747 hasConceptScore W3014201747C108771440 @default.
- W3014201747 hasConceptScore W3014201747C119857082 @default.
- W3014201747 hasConceptScore W3014201747C120936955 @default.
- W3014201747 hasConceptScore W3014201747C127413603 @default.
- W3014201747 hasConceptScore W3014201747C136197465 @default.
- W3014201747 hasConceptScore W3014201747C150899416 @default.
- W3014201747 hasConceptScore W3014201747C154945302 @default.
- W3014201747 hasConceptScore W3014201747C15744967 @default.
- W3014201747 hasConceptScore W3014201747C175154964 @default.
- W3014201747 hasConceptScore W3014201747C19417346 @default.
- W3014201747 hasConceptScore W3014201747C201995342 @default.
- W3014201747 hasConceptScore W3014201747C2780451532 @default.
- W3014201747 hasConceptScore W3014201747C28006648 @default.
- W3014201747 hasConceptScore W3014201747C33923547 @default.
- W3014201747 hasConceptScore W3014201747C41008148 @default.
- W3014201747 hasLocation W30142017471 @default.
- W3014201747 hasLocation W30142017472 @default.
- W3014201747 hasOpenAccess W3014201747 @default.
- W3014201747 hasPrimaryLocation W30142017471 @default.
- W3014201747 hasRelatedWork W1992587951 @default.
- W3014201747 hasRelatedWork W2186494677 @default.
- W3014201747 hasRelatedWork W2578423033 @default.
- W3014201747 hasRelatedWork W2763224350 @default.
- W3014201747 hasRelatedWork W3014201747 @default.
- W3014201747 hasRelatedWork W3031818154 @default.
- W3014201747 hasRelatedWork W3105036711 @default.
- W3014201747 hasRelatedWork W4225294552 @default.
- W3014201747 hasRelatedWork W4298054086 @default.
- W3014201747 hasRelatedWork W4307205255 @default.
- W3014201747 hasVolume "67" @default.
- W3014201747 isParatext "false" @default.
- W3014201747 isRetracted "false" @default.
- W3014201747 magId "3014201747" @default.
- W3014201747 workType "article" @default.