11 March 2010
Venue: Skeel Lecture Theatre, People's Palace, Mile End
'Unified modelling of Uncertainty'
Martin Neil, Professor of Computer Science and Statistics
For too long predictive model builders have failed to exploit domain expertise for the simple reason that human experience is not easily amenable to machine analysis, especially in 'messy' domains. This talk presents a 'unified model' as a method and means for combining expertise and data using statistical and machine learning methods to produce better intelligence. Consideration will be given to how elements of computer science, statistics and machine learning and psychology helps deliver this unified modelling approach. Real applications in the law, medicine, systems engineering and security will be used to illustrate the approach.
Martin Neil is Professor in the Department of Computer Science, Queen Mary where he teaches decision and risk analysis and software engineering. Martin is also a joint founder and Chief Technology Officer of Agena Ltd and a visiting Professor in the Faculty of Engineering and Physical Sciences, University of Surrey. His interests cover Bayesian modeling and/or risk quantification in diverse areas: operational risk in finance, systems and design reliability, software project risk, decision support, simulation cost benefit analysis, AI and personalization, and statistical learning. Before joining Queen Mary Martin was at City University and held senior positions with JP Morgan and Lloyds Register in the areas of software project governance and safety critical systems evaluation respectively.