Andrew Perfors
Home
Research
People
Publications
Outreach
Resources
Blog
CV
Contact
categorisation
The relevance of labels in semi-supervised learning depends on category structure
Learning time-varying categories
The role of sampling assumptions in generalization with multiple categories
Anticipating changes: Adaptation and extrapolation in category learning
Hypothesis generation, the positive test strategy, and sparse categories
Reveals that positive tests are a rational strategy in a world (like ours) where most hypotheses (and categories) are sparse.
Learning time-varying categories
Learning to learn categories
Learnability, representation, and language: A Bayesian approach
Learning overhypotheses
«
Cite
×