Lecturer, Department of Computer Science
University College London
London WC1E 6BT
Phone: +44 (0)20 7679 3684
My research currently focuses on the problem predicting a labeling a graph. This problem is foundational for transductive and semi-supervised learning. Initial bounds and experimental results are given in Online learning over graphs. The paper Prediction on a graph with a perceptron significantly improves on previous results in terms of the tightness and interpretability of the bounds. In the recent work A fast method to predict the labeling of a tree we've developed methods to speed up graph prediction methods. I am also broadly interested in online learning, see my publications page for more details.
I am affiliated with Centre for Computational Statistics and Machine Learning (CSML)
I am programme director for the MSc in Machine Learning (formerly Intelligent Systems). Machine learning is a sub-discipline of computer science which studies the process of automatic inference from data. This field draws on ideas and methods from a diversity of perspectives and disciplines such as artificial intelligence, connectionism, optimization, pattern recognition, and statistics. The commercial successes of machine learning are widespread, some well-known examples are in speech recognition, robotic vision, online ad-placement, fraud detection, and bioinformatics. The MSc Machine Learning is aimed at students trained in computer science or another quantitative science. This MSc is designed to train the student in both the practical and theoretical sides of machine learning and is aimed to prepare the student for either an industrial career or for PhD study. I encourage you to contact me if you should have any questions about this MSc.
I teach the following courses: