Advanced data processing in nuclear and subnuclear physics

Course guarantor:

Miroslav Myška

Lecturer:

Petr Chaloupka, Miroslav Myška

Tutor:

Petr Chaloupka

Supervisor:

Department of Physics

Synopsis:

The student will gain theoretical and practical experience with the use of advanced techniques of statistical data analysis, which are currently used in the processing of data in high-energy physics experiments. These include, for example, unfolding, methods based on the Kálmán filter and machine learning methods such as decision trees and neural networks. The theoretical foundations of regression and classification will be discussed. The student will acquire practical knowledge of methods related to data pre-processing, training of machine learning algorithms (supervised machine learning), reliability validation (bias) and overtraining (overtraining). The aim of the exercise is to analyze real experimental data from the open HEPData database and in practice to compare classifiers obtained by different methods.

Requirements:

Syllabus of lectures:

1. Theory of statistical regression and inference

2. Statistical deconvolution methods

3. Optimization and the Kálmán filter

4. Non-parametric methods of regression and classification

4.1. Decision trees

4.2. Neural networks

Syllabus of tutorials:

Study Objective:

The student will gain theoretical and practical experience with the use of advanced techniques of statistical data analysis, which are currently used in the processing of data in high-energy physics experiments. These include, for example, unfolding, methods based on the Kálmán filter and machine learning methods such as decision trees and neural networks. The theoretical foundations of regression and classification will be discussed. The student will acquire practical knowledge of methods related to data pre-processing, training of machine learning algorithms (supervised machine learning), reliability validation (bias) and overtraining (overtraining). The aim of the exercise is to analyze real experimental data from the open HEPData database and in practice to compare classifiers obtained by different methods.

Study materials:

Required literature:

[1] Bohm, Zech, Introduction to Statistics and Data Analysis for Physicist, DESY online library

[2] I. Goodfellow, Y. Bengio, and A. Courville: Deep Learning, MIT Press, 2016

[3] B. Ristic, S. Arulampalam, N. Gordon: Beyond the Kalman Filter: Particle Filters for Tracking Applications,

Artech House, 2004

Recommended literature:

[4]A. Geron: Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and

Techniques to Build Intelligent Systems, O’Reilly Media, 2019

[5] B. Hachman: A Living Review of Machine Learning for Particle Physics, github: HEPML-LivingReview

Note:

Time-table for winter semester 2024/2025:

Time-table is not available yet

Time-table for summer semester 2024/2025:

Time-table is not available yet

The course is a part of the following study plans: