URL study guide
https://tue.osiris-student.nl/onderwijscatalogus/extern/cursus?cursuscode=2IRR50&collegejaar=2026&taal=enDescription
* Introduction to machine learning and optimization; Instructions: Python for Data Mining and Machine Learning; Recap mathematical basics* Regression (linear and non-linear): regularization, bias-variance trade-off, Ridge regression, Lasso
* Classification: Naive Bayes, k-Nearest Neighbors, Support vector machines and the kernel trick, Decision Trees and Random Forests; Evaluation of classifiers
* Neural Networks (Multi-layer Perceptrons and Convolutional Neural Networks), Backpropagation, Stochastic Gradient Descent, training techniques
* Unsupervised Learning: PCA, SVD, Recommender systems, K-Means clustering, Kernel k-means and Spectral Clustering
The course content is detailed in the accompanying Jupter book
Objectives
The main focus of this course is on the theoretical and statistical foundations of Machine Learning with particular emphasis on modelling assumptions, estimation and evaluation. A secondary focus is on low-level practical aspects (e.g. vanilla implementations of various models and algorithms). After completing the course, students will be able to:* analyze and assess the suitability of common machine learning methods for a given learning problem based on their underlying assumptions and statistical properties of the data
* compare weaknesses and strengths of common machine learning methods in terms of bias-variance trade-offs, generalization and robustness
* implement some of the most widely used methods and tackle limitations of naive implementations, such as numerical issues arising in practice
* critically reflect on model choice, theoretical guarantees and the impact of chosen evaluation metrics on empirical results