I design machine learning algorithms that try to solve some of today's most challenging problems in computer science and statistics.

I adapt ideas from physics and the statistical sciences, and use them in algorithms that can be applied to areas such as: bioinformatics, artificial intelligence, pattern recognition, document information retrieval, and human-computer interaction.

Click on the following topics to see research descriptions and some papers:-

Nonparametric Bayes - powerful nonparametric text/document modelling
Variational Bayesian Methods - approximate Bayesian learning and inference
Bioinformatics - microarray analysis using variational Bayes
Embedded Hidden Markov Models - a novel tool for time series inference
Probabilistic Sensor Fusion - combining modalities using Bayesian graphical models
Collaborators - people I have worked with

Probabilistic Sensor Fusion

In most systems that handle digital media, audio and video data streams are treated separately. Such systems usually have subsystems that are specialised for the different modalities and these are optimised separately. This research examines a novel way to exploit the statistical dependencies between audio and video modalities, using Bayesian networks, or probabilistic graphical models. This is work done at the Microsoft Research labs in Redmond, WA, namely in David Heckerman's Machine Learning and Applied Statistics group.

Videos of the algorithm performance can be viewed at our ICASSP'02 page.

audio

combined
audio-video

video

A principled combination of audio stream (top) and video sequence (selected frames shown) provides superior inference of speaker location, as compared to audio only or video only tracking.