Snell et al.: episodically learned prototype-space classification

What changed

Learned an embedding in episodic few-shot tasks and classified queries by distance to each support class's mean embedding, extending the same prototype framework to description-based zero-shot cases.

Scientific scope

Learned an embedding in episodic few-shot tasks and classified queries by distance to each support class's mean embedding, extending the same prototype framework to description-based zero-shot cases. Nearest-class-mean classification and metric learning are inherited. Generalization depends on the learned embedding and task distribution; no human-level or arbitrary new-class guarantee.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Nearest-class-mean classification and metric learning are inherited. Generalization depends on the learned embedding and task distribution; no human-level or arbitrary new-class guarantee.

Contributors

• Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.

• Prototypical Networks for Few-shot Learning

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction