Machine learning is concerned with developing algorithms that are able to improve their performance by learning from experience.

This normally involves forming a model from a set of training examples that can successfully generalise the regularities in the data to provide predictions for unseen examples or to help to understand the data, by visualisation or identifying relationships between variables of interest.  Machine learning has become a vital tool in exploiting the vast amounts of data generated by modern high-throughput experimental techniques, such as DNA sequencing, gene expression micro-array, protein structure determination and forms of genetic variation analysis (e.g. SNPs.  Applications in computational biology are a rich source of interesting problems for machine learning techniques as the data are often non-vectorial (for instance stings or graphs) and often violate traditional statistical assumptions (for instance the data are an i.i.d. sample).

Research Team

Dr. Gavin Cawley, Dr. Nicola Talbot,  Dr. Wenjia Wang