Machine learning as a subfield of artificial intelligence (AI) is the science of the design of algorithms that can learn through experience acquired from data, without being explicitly programmed. This course provides an introduction to the topic of machine learning and provides knowledge on the core concepts needed by AI scientists. Throughout the course, students will get familiar with the fundamental concepts in the design of effective machine learning algorithms, and different classes of machine learning models. They further gain the practical skills needed to apply machine learning algorithms to new problems.
After this course the students are able to:
Characterize and recognizing the design principles of machine learning algorithms (i.e., Representation, Optimization)
Categorize and differentiate between available machine learning algorithms
- Classification (e.g., SVM, random forest, artificial neural networks)
- Clustering (e.g., K-means, dbscan, auto-encoders)
Evaluate and assess the performance of different machine learning algorithms
Formulate new machine learning problems and apply available algorithms to solve them
The most updated version of the timetables can be found on the students' website:
Written examination with closed questions (50%)
The final grade for the course is established by determining the weighted average. However, both partial grades need to above the passing margin. There is an opportunity to retake the exam.
The teacher will inform the students how the inspection of and follow-up discussion of the exams will take place.
Will be announced later.