Lecture - Introduction

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Error propagation

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Information, inference and confidence level intervals

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Least Squares Fitting

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Maximum Likelihood, Sandwich estimator, Bootstrap

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Markov Chain Monte Carlo, COWs

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - sPlot, sFit, Unfolding

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Lecture - Unfolding, Harmonic analysis

• Michael Schmelling (Max Planck Society (DE))

Exercises

• Jan Peter Wagner (Technische Universitaet Dortmund (DE))

Automatic Differentiation

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

Exercises - Automatic Differentiation [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/1_automatic_differentiation.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/1_automatic_differentiation.jl)

Machine Learning (loss, ROC)

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides - lecture-1B-entropy.jl: introduction to entropy - lecture-1B-mse.jl: MSE as the simplest loss function

Exercises - Samples, FoM, ROC [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/2_samples_fom_roc.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/2_samples_fom_roc.jl)

Decision Trees, Adaboost

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides - lecture-2A-split.jl: splitting index demonstration - lecture-2A-trees.jl: decision tree demonstration

Exercises - Decision Trees [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/3_decision_trees.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/3_decision_trees.jl)

Decision Trees, GradientBoost

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides - [GBDT playground](https://arogozhnikov.github.io/2016/07/05/gradient_boosting_playground.html)

Exercises - AdaBoost, GradientBoost [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/4_boosting.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/4_boosting.jl)

Neural Networks : General introduction

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides - lecture-3A-xor.jl: learning xor demonstrator - gradient descent app: github.com/lilipads/gradient_descent_viz

Exercises - Neural Networks [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/5_neural_networks.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/5_neural_networks.jl)

Neural networks : Bias-Variance TradeOff and regularization techniques

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides: Lecture 3 pdf contains but A,B parts - lecture-3B-UAT.jl: Universal approximation theory demonstration - lecture-3B-NMIST.jl: training of MNIST classification - playground.tensorflow.org

Exercises - NNs on example data [Exercise notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/6_neural_networks.jl) [Solution notebook](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/solutions/6_neural_networks.jl)

Generative networks, Normalizing flow

• Mikhail Mikhasenko (Ruhr Univeristy Bochum)

- Slides - lecture-4A-transformations.jl: demonstration of bijectors - lecture-4A-RQS.jl: tuning RQS

Exercises - Normalizing flow [Notebook NF basics](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/7_normalizing_flow_basics.jl) [Notebook NF training](https://github.com/RUB-EP1/Data-Analysis-Block-Course-2025/blob/main/exercises/8_normalizing_flow.jl)

BBQ Sign up here: https://hackmd.e5.physik.tu-dortmund.de/3XzYG8C4ScuKaNh43QB3GQ?both Location: https://maps.app.goo.gl/qwZvu8eUB14JzKTw5

Written Exam (in person, in Dortmund and Bochum) - Pen and paper, calculator (non-programmable) - Time: 1:30h - 5-6 Problems - ChatGPT is not allowed