skip to content

Department of Computer Science and Technology

 

Research by the Artificial Intelligence Group is multi-disciplinary, spanning genomics and bio-informatics, machine learning, stochastic algorithms, game theory, automated theorem proving, computer vision, and human-like computation. A unifying theme is to understand multi-scale pattern recognition problems, seeking powerful statistical algorithms for modeling and solving them, and for learning from data.

Work by Pietro Lio uses machine learning approaches to analyse bio-medical “big data” for disease modeling and development of personalised medicine, with integration across scales from the molecular and genomic to organ and systems levels. Work by Sean Holden applies Bayesian inference, probabilistic programming, and computational learning theory to drug design, proteomics, and theorem proving.

Mateja Jamnik develops computational models of human reasoning, especially mathematics (for example, diagrammatic reasoning and theorem proving). Her work extends to human-computer interaction and cognitive science. Thomas Sauerwald uses graph theory, game theory, and randomised algorithms such as Markov chains and random walks, to model distributed computing, load balancing, and complex networks. John Daugman has applied his work in computer vision and pattern recognition to create the algorithms used worldwide for automatic recognition of persons by the complex random patterns visible in the iris of the eye. These algorithms have been deployed by the Government of India to enroll all their 1.25 billion citizens in a national ID, welfare distribution, and e-government scheme.

The AI Group seeks to continue to find synergies amongst ideas based in statistics, machine learning and reasoning, cognitive science, biology and engineering, and to develop practical and beneficial applications from them.