Computational Intelligence SEW
This course is held in two parts: The first part is taught by Anand Subramoney and Guillaume Bellec (VO and UE) from the Institute of Theoretical Computer Science, the second part by Franz Pernkopf (VO) and Christian Knoll (UE) from the Institute of Signal Processing and Speech Communication.
Aims and objectives of the course: Knowledge of the most important concepts and methods form the areas machine learning, neural networks, statistical modelling and classification.
- Introduction to Machine Learning
- Simple Regression and Classification Algorithms
- Learning Algorithms for Neural Networks
- Practical Classification Algorithms
- Unsupervised Learning
- Hidden Markov Models
- Graphical Models
There are no particular courses which must be taken as prerequisites for this course. Although there will be introductory examples to Python in the beginning of the exercises, it is recommended to have already some basic knowledge and experience in it. We also assume elementary mathematical knowledge in probability theory, statistics, analysis and calculus.
Exam for the lecture course
The exam consists of two parts, one for the IGI and one for the SPSC part of the course. A positive grade is only possible if both parts of the exam are positive (>50%) individually.
Anand and Guillaume – Tuesdays 15:00-16:00 at Inffeldgasse 16b/1.
This page has information on how to install Python on your computer.
Here you can find material for the lecture course.
Lecture Material is also in the TeachCenter.
Here you can find slides and material for the problem classes.
You can find the assignments and corresponding information here.
Here you can find some online tutorials that were used some years ago. Some still contain relevant information about the course, so we decided to keep them online. However, we can not guarantee that the Matlab code still works on current Matlab versions.
Reading tips and a bibliography are found here.