Application of Deep Learning Technique to an Analysis of Hard Scattering Processes at Colliders

TL;DR

This paper explores advanced deep learning methods, including hyperparameter tuning, boosting, and AutoML, to enhance the analysis of hard scattering processes at colliders, specifically focusing on top quark classification.

Contribution

It introduces optimized deep learning techniques and AutoML applications tailored for collider physics, improving classification accuracy in high energy physics analyses.

Findings

Enhanced classification performance with hyperparameter tuning

Effective boosting on classification errors

AutoML algorithms improve collider data analysis

Abstract

Deep neural networks have rightfully won the place of one of the most accurate analysis tools in high energy physics. In this paper we will cover several methods of improving the performance of a deep neural network in a classification task in an instance of top quark analysis. The approaches and recommendations will cover hyperparameter tuning, boosting on errors and AutoML algorithms applied to collider physics.