Article

Supervised learning outperforms unsupervised learning only for categories of intermediate difficulty

2024-09-20

Abstract excerpt

<p>Humans learn about the world both when supervision is present and when it is absent. The degree to which existing internal representations align with task demands affects how supervised and unsupervised learning progress. However, mixed results in the literature demand a systematic test of whether supervision is particularly beneficial when tasks align (or misalign) with internal representations. We assessed a...

Topics

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

Identifiers and source

Literature Corpus work: f79fcf20-d382-540b-a976-d22835b02e2c
DOI: 10.31234/osf.io/3rfjk

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Supervised learning outperforms unsupervised learning only for categories of intermediate difficultyDOI 10.31234/osf.io/3rfjkRead

Auditory category learning is robust across training regimesSemantic proximity Read

Supervision, Category Structure, and Selective Attention in Category Learning: A Comparative ApproachSemantic proximity Read

A unified mechanism for statistical learning? Evidence from multimodal integration during learningSemantic proximity Read

Algebraic structures emerge from the self-supervised learning of natural soundsSemantic proximity Read

Brain-like dynamics in speech representations can emerge through self-supervised learningSemantic proximity Read

System alignment supports cross-domain learning and zero-shot generalisationSemantic proximity Read

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

Memory for Incidentally Learned Categories Evolves in the Post-Learning IntervalSemantic proximity Read