Skip to content
conftrace_
2010 NeurIPS NeurIPS 2010

Learning the context of a category

Abstract

This paper outlines a hierarchical Bayesian model for human category learning that learns both the organization of objects into categories, and the context in which this knowledge should be applied. The model is fit to multiple data sets, and provides a parsimonious method for describing how humans learn context specific conceptual representations.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Interdisciplinary
🐣 Hot Topic Early Bird - probabilistic model

Authors

Dan Navarro

Topics

Artificial Intelligence > Bayesian & Probabilistic > Bayesian Learning Machine Learning > Core Methods > Representation Learning Interdisciplinary > Cognitive Science > Cognitive Modeling Machine Learning > Bayesian & Probabilistic > Bayesian Learning

Keywords

human learning probabilistic modeling cognitive modeling category learning context modeling context-specific representations context specific probabilistic model hierarchical bayesian model context learning conceptual representation
Download PDF

More from NeurIPS 2010

All NeurIPS 2010 papers →
Batch Bayesian Optimization via Simulation Matching
Inference with Multivariate Heavy-Tails in Linear Models
Towards Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models
Learning via Gaussian Herding
Monte-Carlo Planning in Large POMDPs
Spatial and anatomical regularization of SVM for brain image analysis