
Detailed information 
Original study plan 
Bachelor's programme Computer Science 2024W 
Objectives 
 Students should be able to explain the fundamental principles of machine learning and its applications in various fields such as signal processing, image processing, natural language processing, process modeling, and life sciences.
 Students should be able to differentiate between different types of machine learning: supervised learning, unsupervised learning, and reinforcement learning.
 Students should be able to explain and apply basic machine learning algorithms such as linear regression, kmeans, nearest neighbor, and principal component analysis.
 Students should be able to evaluate machine learning models using various metrics such as cross tabulation/contingency tables and ROC curves.
 Students should be able to explain and utilize advanced methods such as support vector machines and random forests.
 Students should acquire basic knowledge of neural networks and deep learning, and be able to program simple neural networks in Python using deep learning frameworks.
 Students should critically reflect on the advantages and disadvantages of different machine learning techniques and their performance in realworld scenarios.
 Students should be able to implement and adapt machine learning models using libraries such as Scikitlearn or TensorFlow.

Subject 
Machine learning is concerned with creating predictive models and inferring relationships by learning from data. Machine learning methods have become indispensable in various fields, such as computer vision, signal processing, speech and language processing, process modeling, life sciences, and so forth. This course features the most essential concepts of machine learning and gives an overview of the most important methods. The methodological subjects are complemented by examples of exciting recent realworld applications of machine learning methods.
 Taxonomy of machine learning: supervised vs. unsupervised learning, reinforcement learning, classification vs. regression
 Examples of basic methods: nearest neighbor, linear regression, kmeans, principal component analysis
 Basics of evaluating machine learning models: confusion tables, ROC curves
 Support vector machines and random forests (+ examples from life sciences)
 Neural networks and Deep Learning (+ examples from image analysis, drug design, and language processing)
 Clustering and biclustering

Criteria for evaluation 
Written exam

Methods 
Slide presentations complemented by online demos and examples presented on the blackboard.
The lecture is also supported by a MOOC, providing videos, compact scripts, and exercises.

Language 
English and French 
Study material 
Electronic course material is made available for download

Changing subject? 
No 
Corresponding lecture 
^{(*)}INBIPVOBIIN: VO Bioinformatics (3 ECTS)

