Bayesian Learning of Neural Networks for Signal/Background Discrimination in Particle Physics

TL;DR

This paper explores Bayesian neural networks for particle physics classification, demonstrating their potential for more robust signal/background discrimination compared to traditional methods.

Contribution

It introduces Bayesian neural networks for particle physics, comparing their performance with conventional neural networks in a specific search for leptoquarks.

Findings

Bayesian neural networks outperform conventional networks in robustness.

Bayesian approach provides more reliable uncertainty estimates.

Improved discrimination between signal and background in particle physics data.

Abstract

Neural networks are used extensively in classification problems in particle physics research. Since the training of neural networks can be viewed as a problem of inference, Bayesian learning of neural networks can provide more optimal and robust results than conventional learning methods. We have investigated the use of Bayesian neural networks for signal/background discrimination in the search for second generation leptoquarks at the Tevatron, as an example. We present a comparison of the results obtained from the conventional training of feedforward neural networks and networks trained with Bayesian methods.