Support Vector Machines in Analysis of Top Quark Production

TL;DR

This paper explores the application of Support Vector Machines to distinguish top quark signal events from background noise, demonstrating its advantages over traditional neural network methods in high-energy physics analysis.

Contribution

It introduces the SVM approach for top quark event classification and compares its effectiveness to conventional analysis techniques.

Findings

SVM outperforms neural networks in signal/background discrimination

SVM provides more robust classification in high-energy physics data

The method improves the accuracy of top quark detection

Abstract

Multivariate data analysis techniques have the potential to improve physics analyses in many ways. The common classification problem of signal/background discrimination is one example. The Support Vector Machine learning algorithm is a relatively new way to solve pattern recognition problems and has several advantages over methods such as neural networks. The SVM approach is described and compared to a conventional analysis for the case of identifying top quark signal events in the dilepton decay channel amidst a large number of background events.