One-Shot Learning with a Hierarchical Nonparametric Bayesian Model
Name
MIT-CSAIL-TR-2010-052.pdf
Size
1.94 MB
Format
Adobe PDF
Checksum (MD5)
65945abf0ce1031cf8ff04d80099ce89
Author(s)
Salakhutdinov, Ruslan
Tenenbaum, Josh
Torralba, Antonio
Advisor(s)
Joshua Tenenbaum
Date Issued
October 13, 2010
Series/Report no.
MIT-CSAIL-TR-2010-052
Abstract
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.
Subjects
hierarchical Bayes
semi-supervised learning
learning to learn
Persistent DSpace Link
