Search Results for author:
Found 5 papers, 2 papers with code
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization.
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages.
Learning to Infer Program Sketches
Our goal is to build systems which write code automatically from the kinds of specifications humans can most easily provide, such as examples and natural language instruction.
The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples
Hierarchical Bayesian methods have the potential to unify many related tasks (e. g. k-shot classification, conditional, and unconditional generation) by framing each as inference within a single generative model.
