Brenden M Lake, Ruslan R Salakhutdinov, Josh Tenenbaum

Massachusetts Institute of Technology; University of Toronto; Massachusetts Institute of Technology

Poster: One-shot learning by inverting a compositional causal process

7:00 – 11:59pm Saturday, December 07, 2013

Harrah's Special Events Center, 2nd Floor

This is part of the Poster Session which begins at 19:00 on Saturday December 7, 2013


Get the paper

People can learn a new visual class from just one example, yet machine learning algorithms typically require hundreds or thousands of examples to tackle the same problems. Here we present a Hierarchical Bayesian model based on compositionality and causality that can learn a wide range of natural (although simple) visual concepts, generalizing in human-like ways from just one image. We evaluated performance on a challenging one-shot classification task, where our model achieved a human-level error rate while substantially outperforming two deep learning models. We also used a "visual Turing test" to show that our model produces human-like performance on other conceptual tasks, including generating new examples and parsing.