URL study guide
https://tue.osiris-student.nl/onderwijscatalogus/extern/cursus?cursuscode=JBI120&collegejaar=2025&taal=enOmschrijving
This course teaches concepts of linear algebra and probability theory necessary for AI applications, and some fundamental concepts in AI and machine learning, including the implementation of the concepts in Python.1. Linear algebra
2. Vector calculus
3. Probability theory
4. Optimization
5. Bayesian networks
6. Classification with Support Vector Machines
Doelstellingen
Upon successful completion of the course, students are able to:- understand the linear algebra concepts that underlay neural networks and basic clustering methods, and implement them using Python;
- explain how to differentiate vector functions, and compute gradients, divergences, and curls;
- explain how backpropogation works in neural networks, linearize vector functions, and apply this in optimization problems;
- understand basic concepts from probability theory such as independence, and derive conditional probabilities given a probability mass function or probability density function;
- explain how optimization is done in different AI methods, and implement basic optimization algorithms in Python;
- explain how inference and parameter learning is done in Bayesian networks, explain what type of AI task can be done with different Bayesian networks, and implement inference and learning algorithms in Python;
- explain how classification is done with support vector machines, explain duality, and implement a support vector machine in Python.