
After this course the student is able:
 to sum up different approximations and forms of learning from data
 to classify data into a priori specified classes, or by constructing/clustering classes a posteriori by using the concept of similarity of data sets
 to construct predictive models given data sets by using analytical functions or complex predictive models based on the deep learning concept
 to optimize the learning machine given data sets by using both deterministic and probabilistic approaches
 to analyze and validate machine learning models
 to synthesize results of the analysis into a meaningful conclusion and to evaluate the quality of data


Machine learning is a buzzword that is often used in today’s technical conversations. But, what it really means? The main goal of the course is to answer this question by giving students a deeper understanding of the principles of machine learning as a method that can automatically identify patterns from data, learn, and make decisions without human intervention. In this respect, two sets of algorithms will be discussed: those that are used to learn from data generated in a specific manner by using known set of inputs, and others that are used when the data generator is not known or is only semiknown. In both of cases, the deterministic and probabilistic versions of learning algorithms will be presented. Furthermore, a specialized design of machines inspired by the function and the structural network of brain nerve cells (neurons) will be introduced. These will be then briefly generalized to deep learning machines representing a complex form of learning in which multiple layers of neural networks are used to learn from data. Finally, students will not only theoretically engage into the topic, but also gain practical experience in applying new techniques in different practical engineering situations spanning the range of applications such as mechanical, civil, electrical, and medical.
Entry requirements description:
Mandatory:
Students need to have a solid background in multivariate calculus and linear algebra. Example is Linear Algebra (201500292). In addition the basic programming skills in Python or Matlab are required.
Recommended:
Basic knowledge on probability theory, such as courses Probabilty Theory and Statistics (201400221), Statistics and Probability (191506103), or similar. Students with a theoretical focus, will find skills obtained from the MSc math courses scientific computing, information theory or complex networks helpful for this.





Master Mechanical Engineering 
Master Civil Engineering and Management 
Master Systems and Control 
Master Electrical Engineering 
Master Applied Mathematics 
  Required materialsBookChristopher M. Bishop: Pattern Recognition and Machine
Learning, Springer 2006. ISBN13: 9780387310732 
 Course materialDeep Learning by Ian Goodfellow and Yoshua Bengio and
Aaron Courville, MIT Press, 2016 (available digitally) 
 Course material 
 Recommended materialsInstructional modesLecturePresence duty   Yes 
 TutorialPresence duty   Yes 

 TestsAssignment(s) and oral exam


 