Advanced Techniques in Data Analysis

Recommended Prerequisites

Basic knowledge of statistics and programming.

Teaching Methods

This course will combine theoretical and practical teaching components, to develop and firm up the bases in statistics necessary for the understanding of the present-day tools and techniques of data science. The concepts will then be applied to the development of analysis projects employing data of an experimental or theoretical nature.

Learning Outcomes

The analysis of scientific data in experimental and theoretical physics has reach a high degree of sophistication. Analysis techniques span a wide range, from data fitting to the classification of signal events in a sea of background through machine learning, or the determination of the significance of a discovery. The objective of this curricular unit is to present these advanced analysis techniques, used for example in experimental particle physics but with widening application in many other areas of physics, technology and even finance. In particular the area of machine learning has had enormous progress in the last few years, which should be reflected in the Physics and Engineering Physics curricula.

Work Placement(s)

No

Syllabus

1. Statistical data analysis

1.1. Base concepts

1.2. Monte Carlo simulation and its use in data analysis

1.3. Multivariate analysis methods 

1.4. Statistical tests and p-values

1.5. Null hypothesis and criteria for a discovery

1.6. Parameter estimation

1.7. Confidence limits

1.8. Determination of experimental sensitivity

1.9. Systematic uncertainties

2. Machine learning

2.1. Machine learning techniques in data analysis

2.2. Supervised learning, unsupervised learning

2.3. Linear models: classification and regression

2.4. Hipotesis testing and ROC curve

2.5. Machine learning techniques

2.6. Deep learning.

Head Lecturer(s)

José Ricardo Morais Silva Gonçalo

Assessment Methods

Assessment
Review and presentation of a scientific article : 10.0%
Frequency: 40.0%
Project: 50.0%

Bibliography

Glen Cowan, Statistical Data Analysis, Oxford University Press, 1998.

Ilya Narsky and Frank C. Porter, Statistical Analysis Techniques in Particle Physics, Wiley, 2014.

Luca Lista, Statistical Methods for Data Analysis in Particle Physics, Springer, 2017.

Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.

A. R. Oganov, ed., Modern methods of crystal structure prediction, Wiley, 2010.

T. Lookman, S. Eidenbenz, F. Alexander, and C. Barnes, eds., Materials Discovery and Design By Means of Data Science and Optimal Learning, Springer, 2018.

Jonathan Schmidt, Mário R. G. Marques, Silvana Botti, and Miguel A. L. Marques, Recent advances and applications of machine learning in solid-state materials science, Psi_k Scientific Highlight Of The Month, March 2019.