| EPSRC Reference: |
GR/M15972/01 |
| Title: |
COMPARISON OF SUPPORT VECTOR MACHINE AND MINIMUM MESSAGE LENGTH METHODS FOR INDUCTION AND PREDICTION |
| Principal Investigator: |
Gammerman, Professor A |
| Other Investigators: |
|
| Researcher Co-Investigators: |
|
| Project Partners: |
|
| Department: |
Computer Science |
| Organisation: |
Royal Holloway, Univ of London |
| Scheme: |
Standard Research (Pre-FEC) |
| Starts: |
01 January 1999 |
Ends: |
31 March 2002 |
Value (£): |
132,787
|
| EPSRC Research Topic Classifications: |
|
| EPSRC Industrial Sector Classifications: |
| Electronics |
Information Technologies |
| Transport Systems and Vehicles |
|
|
| Related Grants: |
|
| Panel History: |
|
|
Summary on Grant Application Form |
|
It is proposed to study two important inductive algorithms (support-vector machine, and minimum message length). The analytical and computational comparison of the algorithms is envisaged as well as comparison with other classical model selection methods. There are some indications that both methods have a closer relationship than is apparent, given their profoundly different philosophical foundations. We aim to elucidate just what relationships exist, by both theoretical analysis and comparison of the mathematics and performance of the two algorithms when applied to the same inductive or predictive situation. For instance, we hope to discover whether the Support-Vector algorithm can have a valid interpretation as minimising the length of some representation of the data, and whether MML algorithms can have a valid interpretation as minimising some form of prediction risk. Positive answers to these questions would allow each method to be described and analysed in the theoretical framework of the other, which analyses could well suggest improvements, extensions and refinements of the two methods. Negative answers would help to clarify the consequences of adopting either a Bayesian or a Confidence approach to prediction and inference.
|
|
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: |
|