Analyzing the Benefits of Prototypes for Semi-Supervised Category Learning

eScholarship, University of California 2024-01-01

Categories can be represented at different levels of abstraction, from prototypes focused on the most typical members to remembering all observed exemplars of the category. These representations have been explored in the context of supervised learning, where stimuli are presented with known category labels. We examine the benefits of prototype-based representations in a less-studied domain: semi-supervised learning, where agents must form unsupervised representations of stimuli before receiving category labels. We study this problem in a Bayesian unsupervised learning model called a variational auto-encoder, and we draw on recent advances in machine learning to implement a prior that encourages the model to use abstract prototypes to represent data. We apply this approach to image datasets and show that forming prototypes can improve semi-supervised category learning. Additionally, we study the latent embeddings of the models and show that these prototypes allow the models to form clustered representations without supervision, contributing to their success in downstream categorization performance.

Artificial Intelligence; Psychology; Concepts and categories; Machine learning; Bayesian modeling; article

Open access content. Open access content
public

application/pdf
Proceedings of the Annual Meeting of the Cognitive Science Society vol 46, iss 0

CDLER oai:escholarship.org:ark:/13030/qt4241h4jx
qt4241h4jx
https://escholarship.org/uc/item/4241h4jx
https://escholarship.org/content/qt4241h4jx/qt4241h4jx.pdf
https://escholarship.org/
1449581409

UC MASS DIGITIZATION
From OAIster®, provided by the OCLC Cooperative.

edsoai.on1449581409