Development of a Vertex Finding Algorithm using Recurrent Neural Network

TL;DR

This paper presents a novel vertex finding algorithm for future lepton colliders using a combination of fully-connected and recurrent neural networks with attention mechanisms, aiming to enhance collider experiment physics reach.

Contribution

It introduces a new neural network-based vertex finding method combining seed detection and track association, improving upon standard algorithms for collider data analysis.

Findings

The RNN with attention mechanism effectively associates tracks to vertex seeds.

The proposed algorithm shows improved accuracy over traditional methods.

Performance comparison indicates potential for enhanced physics analysis at colliders.

Abstract

Deep learning is a rapidly-evolving technology with possibility to significantly improve physics reach of collider experiments. In this study we developed a novel algorithm of vertex finding for future lepton colliders such as the International Linear Collider. We deploy two networks; one is simple fully-connected layers to look for vertex seeds from track pairs, and the other is a customized Recurrent Neural Network with an attention mechanism and an encoder-decoder structure to associate tracks to the vertex seeds. The performance of the vertex finder is compared with the standard ILC reconstruction algorithm.