One-Shot Learning with a Hierarchical Nonparametric Bayesian Model
Author(s)
Salakhutdinov, Ruslan; Tenenbaum, Josh; Torralba, Antonio
DownloadMIT-CSAIL-TR-2010-052.pdf (1.935Mb)
Other Contributors
Computational Cognitive Science
Advisor
Joshua Tenenbaum
Metadata
Show full item recordAbstract
We develop a hierarchical Bayesian model that learns to learn categories from single training examples. The model transfers acquired knowledge from previously learned categories to a novel category, in the form of a prior over category means and variances. The model discovers how to group categories into meaningful super-categories that express different priors for new classes. Given a single example of a novel category, we can efficiently infer which super-category the novel category belongs to, and thereby estimate not only the new category's mean but also an appropriate similarity metric based on parameters inherited from the super-category. On MNIST and MSR Cambridge image datasets the model learns useful representations of novel categories based on just a single training example, and performs significantly better than simpler hierarchical Bayesian approaches. It can also discover new categories in a completely unsupervised fashion, given just one or a few examples.
Date issued
2010-10-13Series/Report no.
MIT-CSAIL-TR-2010-052
Keywords
hierarchical Bayes, semi-supervised learning, learning to learn