Applicability Evaluation of Selected xAI Methods for Machine Learning Algorithms for Signal Parameters Extraction

Abstract

Machine learning methods find growing application in the reconstruction and analysis of data in high energy physics experiments. A modified convolutional autoencoder model was employed to identify and reconstruct the pulses from scintillating crystals. The model was further investigated using four xAI methods for deeper understanding of the underlying reconstruction mechanism. The results are discussed in detail, underlining the importance of xAI for knowledge gain and further improvement of the algorithms.

References in corpus (8)

• Axiomatic Attribution for Deep Networks
• Deep Learning and its Application to LHC Physics
• Exploring QCD matter in extreme conditions with Machine Learning
• On the (In)fidelity and Sensitivity for Explanations
• Explainable machine learning of the underlying physics of high-energy particle collisions
• Occlusion Sensitivity Analysis with Augmentation Subspace Perturbation in Deep Feature Space
• Explainable AI for High Energy Physics
• Using Artificial Intelligence in the Reconstruction of Signals from the PADME Electromagnetic Calorimeter

Cited by in corpus (2)

• Development and Explainability of Models for Machine-Learning-Based Reconstruction of Signals in Particle Detectors
• The Physics Behind ML-based Quark-Gluon Taggers