- Abstract: Given a large database of concepts but only one or a few examples of each, can we learn models for each concept that are not only generalisable, but interpretable? In this work, we aim to tackle this problem through hierarchical Bayesian program induction. We present a novel learning algorithm which can infer concepts as short, generative, stochastic programs, while learning a global prior over programs to improve generalisation and a recognition network for efficient inference. Our algorithm, Wake-Sleep-Remember (WSR), combines gradient learning for continuous parameters with neurally-guided search over programs. We show that WSR learns compelling latent programs in two tough symbolic domains: cellular automata and Gaussian process kernels. We also collect and evaluate on a new dataset, Text-Concepts, for discovering structured patterns in natural text data.
- Keywords: wake-sleep, variational, amortised inference, hierarchical bayes, program learning
- TL;DR: We extend the wake-sleep algorithm and use it to learn to learn structured models from few examples,