Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108142528> ?p ?o ?g. }
- W3108142528 abstract "Cognitive control, the ability of a system to adapt to the demands of a task, is an integral part of cognition. A widely accepted fact about cognitive control is that it is context-sensitive: Adults and children alike infer information about a task's demands from contextual cues and use these inferences to learn from ambiguous cues. However, the precise way in which people use contextual cues to guide adaptation to a new task remains poorly understood. This work connects the context-sensitive nature of cognitive control to a method for meta-learning with context-conditioned adaptation. We begin by identifying an essential difference between human learning and current approaches to meta-learning: In contrast to humans, existing meta-learning algorithms do not make use of task-specific contextual cues but instead rely exclusively on online feedback in the form of task-specific labels or rewards. To remedy this, we introduce a framework for using contextual information about a task to guide the initialization of task-specific models before adaptation to online feedback. We show how context-conditioned meta-learning can capture human behavior in a cognitive task and how it can be scaled to improve the speed of learning in various settings, including few-shot classification and low-sample reinforcement learning. Our work demonstrates that guiding meta-learning with task information can capture complex, human-like behavior, thereby deepening our understanding of cognitive control." @default.
- W3108142528 created "2020-12-07" @default.
- W3108142528 creator A5006661033 @default.
- W3108142528 creator A5025205227 @default.
- W3108142528 creator A5035392658 @default.
- W3108142528 creator A5077079119 @default.
- W3108142528 creator A5083919055 @default.
- W3108142528 date "2020-11-27" @default.
- W3108142528 modified "2023-09-27" @default.
- W3108142528 title "Connecting Context-specific Adaptation in Humans to Meta-learning" @default.
- W3108142528 cites W1571434348 @default.
- W3108142528 cites W1594201624 @default.
- W3108142528 cites W1598377843 @default.
- W3108142528 cites W1602500555 @default.
- W3108142528 cites W1685858428 @default.
- W3108142528 cites W1962416794 @default.
- W3108142528 cites W2000998192 @default.
- W3108142528 cites W2026921170 @default.
- W3108142528 cites W2041336675 @default.
- W3108142528 cites W2061304498 @default.
- W3108142528 cites W2093397813 @default.
- W3108142528 cites W2103185517 @default.
- W3108142528 cites W2111526438 @default.
- W3108142528 cites W2118781169 @default.
- W3108142528 cites W2121863487 @default.
- W3108142528 cites W2126204609 @default.
- W3108142528 cites W2131802924 @default.
- W3108142528 cites W2132622533 @default.
- W3108142528 cites W2134266007 @default.
- W3108142528 cites W2138455848 @default.
- W3108142528 cites W2140956413 @default.
- W3108142528 cites W2150104440 @default.
- W3108142528 cites W2152570982 @default.
- W3108142528 cites W2158782408 @default.
- W3108142528 cites W2170329722 @default.
- W3108142528 cites W2170434170 @default.
- W3108142528 cites W2189089430 @default.
- W3108142528 cites W2398118205 @default.
- W3108142528 cites W2528909307 @default.
- W3108142528 cites W2601450892 @default.
- W3108142528 cites W2787757704 @default.
- W3108142528 cites W2808195305 @default.
- W3108142528 cites W2888816922 @default.
- W3108142528 cites W2895560838 @default.
- W3108142528 cites W2902729397 @default.
- W3108142528 cites W2904167876 @default.
- W3108142528 cites W2913350117 @default.
- W3108142528 cites W2923504512 @default.
- W3108142528 cites W2944900455 @default.
- W3108142528 cites W2947247301 @default.
- W3108142528 cites W2949117887 @default.
- W3108142528 cites W2950728319 @default.
- W3108142528 cites W2950763986 @default.
- W3108142528 cites W2952425013 @default.
- W3108142528 cites W2962723986 @default.
- W3108142528 cites W2962849793 @default.
- W3108142528 cites W2963279277 @default.
- W3108142528 cites W2963281204 @default.
- W3108142528 cites W2963341924 @default.
- W3108142528 cites W2963580001 @default.
- W3108142528 cites W2963581679 @default.
- W3108142528 cites W2963921132 @default.
- W3108142528 cites W2964078140 @default.
- W3108142528 cites W2967684355 @default.
- W3108142528 cites W2970941416 @default.
- W3108142528 cites W2981344907 @default.
- W3108142528 cites W3032377877 @default.
- W3108142528 cites W3099903704 @default.
- W3108142528 cites W567721252 @default.
- W3108142528 cites W93016980 @default.
- W3108142528 hasPublicationYear "2020" @default.
- W3108142528 type Work @default.
- W3108142528 sameAs 3108142528 @default.
- W3108142528 citedByCount "0" @default.
- W3108142528 crossrefType "posted-content" @default.
- W3108142528 hasAuthorship W3108142528A5006661033 @default.
- W3108142528 hasAuthorship W3108142528A5025205227 @default.
- W3108142528 hasAuthorship W3108142528A5035392658 @default.
- W3108142528 hasAuthorship W3108142528A5077079119 @default.
- W3108142528 hasAuthorship W3108142528A5083919055 @default.
- W3108142528 hasConcept C107457646 @default.
- W3108142528 hasConcept C139807058 @default.
- W3108142528 hasConcept C151730666 @default.
- W3108142528 hasConcept C154945302 @default.
- W3108142528 hasConcept C15744967 @default.
- W3108142528 hasConcept C162324750 @default.
- W3108142528 hasConcept C169760540 @default.
- W3108142528 hasConcept C169900460 @default.
- W3108142528 hasConcept C180747234 @default.
- W3108142528 hasConcept C187736073 @default.
- W3108142528 hasConcept C2775924081 @default.
- W3108142528 hasConcept C2779343474 @default.
- W3108142528 hasConcept C2780451532 @default.
- W3108142528 hasConcept C2781002164 @default.
- W3108142528 hasConcept C41008148 @default.
- W3108142528 hasConcept C86803240 @default.
- W3108142528 hasConcept C97541855 @default.
- W3108142528 hasConceptScore W3108142528C107457646 @default.
- W3108142528 hasConceptScore W3108142528C139807058 @default.
- W3108142528 hasConceptScore W3108142528C151730666 @default.