Περιεχόμενα: Introduction to machine learning, the cross validation method, introduction to probability theory and probabilistic models, linear regression and logistic regression models, nonlinear models, neural networks and deep learning, deep learning architectures, introduction to large language models, knearest neighbors, descriptive probabilistic classification models, naive Bayes, support vector machines, decision trees and information gain, ensemble methods, clustering methods, k-means algorithm, dimensionality reduction methods, reinforcement learning.

Assessment: The final course grade is based on three criteria: (1) Performance on the first assignment (20%); (2) Performance on the second assignment (20%); (3) Final written exams (60%). A prerequisite for the exam to be considered successful is that at least a grade equal to 5 is achieved in each category of grading criteria (ie, Assignments and Final Exam).