EPSRC logo

Details of Grant 

EPSRC Reference: GR/T18707/01
Title: Novel machine learning methods based on techniques from approximation, estimation & computation
Principal Investigator: Pontil, Professor M
Other Investigators:
Researcher Co-Investigators:
Project Partners:
State Universities of New York (Grouped)
Department: Computer Science
Organisation: UCL
Scheme: First Grant Scheme Pre-FEC
Starts: 01 October 2004 Ends: 31 January 2008 Value (£): 123,766
EPSRC Research Topic Classifications:
Artificial Intelligence Fundamentals of Computing
EPSRC Industrial Sector Classifications:
Information Technologies
Related Grants:
Panel History:  
Summary on Grant Application Form
Over the past ten years the diffusion of powerful computers has provided the opportunity to apply Machine Learning techniques to the analysis of complex amount of data such as, for example, images, biological sequences, and text documents. This empirical study has in turn driven the discovery of new Machine Learning methods and their use has made possible significant progress in several empirical fields, some important, for example, for national security, medical diagnosis, and e-business. A remarkable example of this synergetic interaction is provided by learning methods based on kernel spaces. The first cycle of research is arguably over and a satisfactory synthesis is now available. But we believe that a deeper study of Machine Learning Theory and, in particular, kernel-based methods, will provide a substantial contribution to advance in those fields which require powerful tools for high-dimensional data analysis. W e propose new approaches based on function approximation for characterising kernel spaces. Such approaches combined with methods from statistical estimation theory and numerical analysis will lead to novel kernel-based learning algorithms. We will implement the algorithms by means of user-friendly software tools, and apply them on three real application problems. These application studies are of interest in their own right but will also help in understanding the strengths and limitations of the proposed methods and to provide a useful synthesis for elucidating the construction of state of the art systems in each application area.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:  
Further Information:  
Organisation Website: