Separating Signal From Background Using Ensembles of Rules
Conference
·
OSTI ID:895817
Machine learning has emerged as a important tool for separating signal events from associated background in high energy particle physics experiments. This paper describes a new machine learning method based on ensembles of rules. Each rule consists of a conjuction of a small number of simple statements (''cuts'') concerning the values of individual input variables. These rule ensembles produce predictive accuracy comparable to the best methods. However their principal advantage lies in interpretation. Because of its simple form, each rule is easy to understand, as is its influence on the predictive model. Similarly, the degree of relevance of each of the respective input variables can be assessed. Graphical representations are presented that can be used to ascertain the dependence of the model jointly on the variables used for prediction.
- Research Organization:
- Stanford Linear Accelerator Center (SLAC)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC02-76SF00515;
- OSTI ID:
- 895817
- Report Number(s):
- SLAC-PUB-12247
- Conference Information:
- Prepared for PHYSTATO5: Statistical Problems in Particle Physics, Astrophysics and Cosmology, Oxford, England, United Kingdom, 12-15 Sep 2005
- Country of Publication:
- United States
- Language:
- English
Similar Records
A Numerical Comparison of Rule Ensemble Methods and Support Vector Machines
Image Change Detection via Ensemble Learning
Technical Report
·
Thu Dec 17 23:00:00 EST 2009
·
OSTI ID:981337
Image Change Detection via Ensemble Learning
Conference
·
Mon Dec 31 23:00:00 EST 2012
·
OSTI ID:1093136