Frank Donald Wood

Associate Professor

Research Classification

Research Interests

Artificial Intelligence
Computational neuroscience
Machine Learning
Natural Language Processing
New models and inference algorithms
Probabilistic models
Probabilistic programming
Probabilistic programming systems
Reinforcement learning

Relevant Degree Programs


Graduate Student Supervision

Master's Student Supervision (2010 - 2021)
On label-efficient computer vision : building fast and effective few-shot image classifiers (2021)

Modern deep learning requires large-scale extensively labelled datasets for training. Few-shot learning aims to alleviate this issue by learning effectively from few labelled examples. In previously proposed few-shot visual classifiers, it is assumed that the feature manifold arriving at the classifier has uncorrelated feature dimensions and uniform feature variance. In this work, we focus on addressing the limitations arising from this assumption by proposing a variance-sensitive class of models that operates in a low-label regime. The first method, Simple CNAPS, employs a hierarchically regularized Mahalanobis-distance based classifier combined with a state of the art neural adaptive feature extractor to achieve strong performance on Meta-Dataset, mini-ImageNet and tiered-ImageNet benchmarks. We further extend this approach to a transductive learning setting, proposing Transductive CNAPS. This transductive method combines a soft k-means parameter refinement procedure with a two-step task encoder to achieve improved test-time classification accuracy using unlabelled data. Transductive CNAPS achieves state of the art performance across all major few-shot learning benchmarks. Finally, we explore the use of our methods (Simple and Transductive) for “out of the box” continual and active learning. Extensive experiments on large scale benchmarks illustrate robustness and versatility of this, relatively speaking, simple class of models. All trained model checkpoints and corresponding source codes are made publicly available at

View record

On amortized inference in large-scale simulators (2020)

Motivated by the problem of amortized inference in large-scale simulators, we introduce a probabilistic programming library that brings us closer to this goal. This library enables us to perform Bayesian inference on any simulator written in a wide variety of programming languages, with minimal modification to the simulator's source code. However, there are challenges in achieving this goal in its most general meaning. In particular, we address the obstacles caused by unbounded loops. Existing approaches to amortized inference in probabilistic programs with unbounded loops can produce estimators with infinite variance. An instance of this is importance sampling inference in programs that explicitly include rejection sampling as part of the user-programmed generative procedure. We develop a new and efficient amortized importance sampling estimator. We prove finite variance of our estimator and empirically demonstrate our method's correctness and efficiency compared to existing alternatives on generative programs containing rejection sampling loops and discuss how to implement our method in a generic probabilistic programming framework.

View record


Membership Status

Member of G+PS
View explanation of statuses

Program Affiliations


If this is your researcher profile you can log in to the Faculty & Staff portal to update your details and provide recruitment preferences.


Read tips on applying, reference letters, statement of interest, reaching out to prospective supervisors, interviews and more in our Application Guide!