Application of Neural Networks for Energy Reconstruction

TL;DR

This paper explores using neural networks to improve energy reconstruction in the CMS detector's calorimetry system, demonstrating enhanced linearity and resolution over traditional methods.

Contribution

It introduces a neural network-based approach for energy reconstruction, showing significant improvements in accuracy and linearity compared to existing weighting techniques.

Findings

Neural networks achieve good linearity in energy reconstruction.

Energy resolution is significantly improved with neural networks.

The method outperforms traditional weighting techniques.

Abstract

The possibility to use Neural Networks for reconstruction of the energy deposited in the calorimetry system of the CMS detector is investigated. It is shown that using feed - forward neural network, good linearity, Gaussian energy distribution and good energy resolution can be achieved. Significant improvement of the energy resolution and linearity is reached in comparison with other weighting methods for energy reconstruction.