Article

Using Compositionality to Learn Many Categories from Few Examples

2024-02-06

Abstract excerpt

<p>Humans have the remarkable ability to learn new categories from few examples, but how few examples can we actually learn from? Recent studies suggest it may be possible to learn more novel concepts than the number of examples. Previous approaches to such less-than-one-shot (LO-shot) learning used soft labels to provide weighted mappings from each example to multiple categories. Unfortunately, people find soft l...

Topics

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

Identifiers and source

Literature Corpus work: deab74cb-e6bb-5f43-898d-a0d9e5cd4659
DOI: 10.31234/osf.io/upn8e

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Using Compositionality to Learn Many Categories from Few ExamplesDOI 10.31234/osf.io/upn8eRead

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

Creating Something Different: Similarity, Contrast, and Representativeness in CategorizationSemantic proximity Read

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

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

Contextual Feature Expansion with Superordinate Concept for Compositional Zero-Shot LearningSemantic proximity Read

Excess Capacity LearningSemantic proximity Read

How we draw and recognize things that don’t existSemantic proximity Read

One shot generalization in humans revealed through a drawing taskSemantic proximity Read

Assembling hierarchies of action using sequencing and abstraction: studies and models of zero-shot learningSemantic proximity Read

Beyond independent latent classes: Testing the limits of human flexibilitySemantic proximity Read

Zero-shot learning of naturalistic concepts via conceptual systems alignmentSemantic proximity Read

Training set coherence and set size effects on concept generalization and recognitionSemantic proximity Read