Article

Building integrated representations through interleaved learning

2021-07-30

Abstract excerpt

Inferring relationships that go beyond our direct experience is essential for understanding our environment. This capacity requires either building representations that directly reflect structure across experiences as we encounter them, or computing the indirect relationships across experiences as the need arises. Building structure directly into overlapping representations allows for powerful learning and general...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 86f57baa-4580-5986-9ad0-2ea75bc777ad
DOI: 10.1101/2021.07.29.454337

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Building integrated representations through interleaved learningDOI 10.1101/2021.07.29.454337Read

An active neural mechanism for relational learning and fast knowledge reassemblySemantic proximity Read

Computational Models Suggest that Human Memory Judgments Exhibit Interference due to the Use of Distributed RepresentationsSemantic proximity Read

Overcoming distortion in multidimensional predictive representationSemantic proximity Read

Replay builds an efficient cognitive map offline to avoid computation onlineSemantic proximity Read

Unifying principles of generalization: past, present, and futureSemantic proximity Read

Motif Learning Facilitates Sequence Memorization and GeneralizationSemantic proximity Read

Concurrent representations of reinstated and transformed memories and their modulation by rewardSemantic proximity Read

Long-Horizon associative learning as a unifying framework for statistical learning across scalesSemantic proximity Read

Statistical learning and retrieval-based inference in the acquired equivalence paradigmSemantic proximity Read

Event integration and temporal differentiation: how hierarchical knowledge emerges in hippocampal subfields through learningSemantic proximity Read

Abstract representations emerge naturally in neural networks trained to perform multiple tasksSemantic proximity Read

Humans and neural networks show similar patterns of transfer and interference during continual learningSemantic proximity Read