Neural Computing Research
Group

Dr Chris Williams


c.k.i.williams@aston.ac.uk
Tel. +44 (0)121 359 3611 x.4382
On July 1 1998 I moved to the Department of Artificial Intelligence at the University of Edinburgh. My homepage there is http://www.dai.ed.ac.uk/daidb/people/homes/ckiw/ and my email address is ckiw@dai.ed.ac.uk. Please update any links accordingly as the continued existence of this page cannot be guaranteed.

Research Interests

I am interested in a wide range of theoretical and practical issues in neural networks/statistical pattern recognition/computer vision. My analysis is usually carried out in a probabilistic reasoning/ Bayesian framework. The main foci of my current research are into prediction with Gaussian processes, and image interpretation

* Over the few years I have been working (with Carl Rasmussen, David Barber and Francesco Vivarelli) on using Gaussian processes (GPs) for regression and classification problems. In a sense Gaussian processes are an alternative to neural networks for prediction, and a key question is how their performance compares with neural networks. Our results indicate a similar level of performance with networks when tested on a suite of real-world problems, and with more straightforward computational methods; GPs are particularly suitable when only a few hundred training examples are available. GPs have some properties which make them easier to analyze then neural nets, and there are also interesting links between networks and GPs. More information can be obtained on GPs from Carl Rasmussen's GP homepage.

* Image interpretation. Object recognition can be cast in a statistical framework (e.g. in work by Grenander). This approach argues for image understanding using generative models, i.e. explaining an image by instantiated objects. In previous work I used this framework to study the performance of deformable models for a character recognition task. Currently I am looking at identifying regions in outdoor scenes using this approach, and there is much work to be done in extending/applying the method.

* I am involved (along with Francesco Vivarelli) in the Validation and Verification of Neural Network Systems project supported by British Aerospace and EPSRC.

Other areas of interest include (i) applications of inference with Gaussian and non-Gaussian random fields (e.g. modelling wind fields) (ii) data visualization (iii) the role of machine learning in computer vision and (iv) trying to understand the processing and representations used in animal visual systems.

Brief Biography

I did Physics at Cambridge, graduating in 1982 (BA in Physics and Theoretical Physics, Class I), and then did a further year of study known as Part III Maths (Distinction, 1983). I was interested in the "neural networks" field at that time, but it was difficult to find anyone to work with. I then switched directions for a while, doing an MSc in Water Resources at the University of Newcastle upon Tyne and going on to work in Lesotho, Southern Africa in low-cost sanitation. In 1988 I returned to academia, studing neural networks/AI with Geoff Hinton at the University of Toronto (MSc 1990, PhD 1994). In September 1994 I moved to Aston University as a Research Fellow and was made a Lecturer in August 1995. My partner Barbara and I have two young daughters, Kate, born in November 1993 and Ruth, born in July 1995. In my remaining spare time I like to go hill-walking and listen to music.

Publications


Pages: NCRG - Who's who
Last modified: Mon Aug 10 18:01:14 BST 1998