Support Vector Machines and generalisation in HEP
February 06, 2017
April 19, 2017
The concept of Support Vector Machines is briefly reviewed and their potential use in high energy physics scenarios is discussed. They have the potential to be less susceptible to over-fitting than artificial neural networks and boosted decisions trees - whose use is common across high energy particle physics. Cross validation is discussed in the context of improving generalisation of machine learning algorithms and preliminary work on bringing more rigor to understanding generalisation in HEP analysis is presented.
How to cite
Metadata are provided both in "article" format (very similar to INSPIRE) as this helps creating
very compact bibliographies which can be beneficial to authors and
readers, and in "proceeding" format
which is more detailed and complete.