Semester 8

Course: Machine Learning

Course Code: ΕΥΗ6
Course Level: Undergratuate
Obligatory/Elective: Elective
Semester: 8
Division: Division of Computers
Group: Group A
ECTS Credits: 5
Hours Per Week: 4
Language: Greek, English
  • Introduction to Machine Learning.
  • Linear Models.
  • Tree Models.
  • Rule Models.
  •  Model Ensembles.
  •  Reinforcement Learning.
  • CNN.
  • GAN.
Learning Outcomes:

Upon successful completion of the course, students will know what is involved in the field of engineering learning, as well as how algorithms for linear models, tree models, rule models, ensembles of models and reinforcement learning work. In addition, they will be able to apply such algorithms to real-world data and applications using Python's scikit-learn and gym libraries.

Retrieve, analyse and synthesise data and information, with the use of necessary technologies

. Adapt to new situations. Make decisions.  Work autonomously. Work in teams. Work in an international context. Appreciate diversity and multiculturality. Respect natural environment

Be critical and self-critical. Advance free, creative and causative thinking. Retrieve, analyse and synthesise data and information, with the use of necessary technologies.

Advance free, creative and causative thinking. 



Teaching Methods:



Written final examination (80%):

- Multiple-choice questions

- Short Answers

- Laboratory Work

- Personal/group project work (20%)

Suggested Books:

[1]   Αναγνωριση Προτυπων Και Μηχανικη Μαθηση, C.M. Bishop, Έκδοση: 1/2019.

[2]   Μηχανικη Μαθηση, Κωνσταντινος Διαμανταρας, Δημητρης Μποτσης, Έκδοση: 1η/2019.

[3]   Νευρωνικά Δίκτυα και Μηχανική Μάθηση, Haykin Simon, Έκδοση: 3η έκδ./2010.

[4]   Αναγνώριση Προτύπων, Theodoridis S. , Έκδοση: 1η έκδ./2011.

Lecturer: Fragulis George