Article

Excess Capacity Learning

2026-04-19

Abstract excerpt

<p>How do humans learn from experience? Traditionally, cognitive scientists have assumed that discovering generalizable patterns requires that humans compress rich and noisy experiences. However, recent computer science results suggest otherwise — systems can learn by ‘overfitting’ and expanding all the details of their experiences. We offer a new perspective on learning based on a cognitive system’s representatio...

Topics

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

Identifiers and source

Literature Corpus work: c196347c-b512-57fd-94a7-44628ff2abeb
DOI: 10.31234/osf.io/vxs6f_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Excess Capacity LearningDOI 10.31234/osf.io/vxs6f_v1Read

No Coincidence, George: Capacity Limits in Cognitive Processing Reflect the Curse of GeneralizationSemantic proximity Read

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

Capacity Limits in Cognitive Processing Reflect the Curse of GeneralizationSemantic proximity Read

Capacity Limits in Cognitive Processing Reflect the Curse of GeneralizationSemantic proximity Read

No Coincidence, George: Processing Limits in Cognitive Function Reflect the Curse of GeneralizationSemantic proximity Read

No Coincidence, George: Processing Limits in Cognitive Function Reflect the Curse of GeneralizationSemantic proximity Read

Human latent-state generalization through prototype learning with discriminative attentionSemantic proximity Read

A neural mechanism for online discovery of latent contextsSemantic proximity Read

A neural network account of memory replay and knowledge consolidationSemantic proximity Read

The Generalization Artist - Or: How Can We Characterize Human Generalization?Semantic proximity Read

CogNGen: Constructing the kernel of a hyperdimensional predictive processing cognitive architectureSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read