Article

Do humans learn like transformer networks?

2024-10-25

Abstract excerpt

<p>Do humans learn like transformers? We trained both humans and transformer networks on a rule learning task where they had to respond to a query at the end of a sequence of symbols (the context). At test, we measured both “in-context” learning (the ability to generalise the rule to novel queries) and “in-weights” learning (the recall of past experiences from memory). Manipulating the diversity and redundancy of...

Topics

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

Uncategorized literature

Identifiers and source

Literature Corpus work: aa557254-7e15-5914-a14c-790d141a8d0c
DOI: 10.31234/osf.io/ryn8d

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Do humans learn like transformer networks?DOI 10.31234/osf.io/ryn8dRead

Excess Capacity LearningSemantic proximity Read

Beyond Words: The Evolution of Large Language Models in Context-AwareSemantic proximity Read

Using Compositionality to Learn Many Categories from Few ExamplesSemantic proximity Read

Basics of Large Language Models - transformers to LLMsSemantic proximity Read

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

Determinants of human compositional generalizationSemantic proximity Read

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

Generalizing Functions in Sparse DomainsSemantic proximity Read

Local versus Global Statistical Learning in LanguageSemantic proximity Read

Local versus Global Statistical Learning in LanguageSemantic proximity Read

The roles of neural networks in language acquisitionSemantic proximity Read

Motif Learning Facilitates Sequence Memorization and GeneralizationSemantic proximity Read