Computer technology touches almost every aspect of our lives, and today computers perform many extraordinary tasks beyond the capabilities of any human. However, there are huge information processing challenges in these tasks – such as recognising everyday objects, translating text between languages, or discovering the genetic origins of human diseases – which lie beyond the reach of conventional computational methods. Remarkably, such problems can be tackled by programming the computer to learn by experience, in much the same way as people do.

This discourse will explore and explain the exciting field of machine learning, and will provide insights into the way in which computers are literally trained to solve difficult tasks. It will be illustrated with graphic examples drawn from diverse areas such as digital photography, handwriting recognition, and even the oriental strategy game of Go.

Christopher Bishop is Deputy Director of Microsoft Research in Cambridge, and is also Professor of Computer Science at the University of Edinburgh. He graduated in physics from Oxford, and has a PhD in theoretical physics from the University of Edinburgh with a thesis on quantum field theory. His research interests include probabilistic approaches to machine learning, as well as their application to fields such as computer vision. He is a Fellow of the British Computer Society and a Fellow of Darwin College, Cambridge. In 2004 he was elected Fellow of the Royal Academy of Engineering and in 2007 he was elected Fellow of the Royal Society of Edinburgh. He holds a commercial pilots licence and for relaxation enjoys flying aerobatics.

Registration required:

Yes

Free:

No