CS-577

Machine Learning

Postgraduate

The purpose of the course is to provide a broad introduction to the field of Machine Learning including the basic theory, principles, and algorithms, as well as practical applications on real problems. The topics focus on supervised classification and include: (1) A brief reminder of basic probabilities. Statistical testing of hypotheses.(2) Supervised learning and learning from examples. Hypotheses space, algorithms for learning predictive and diagnostic models and classification models (Decision Trees, Random Forests, Support Vector Machines, Artificial Neural Networks, Naive Bayes, K-Nearest Neighbors)(3) Metrics for measuring performance and the Area Under the Receiver΄s Operating Characteristic Curve.(4) Estimation of predictive performance and accuracy, theory and algorithms for model selection, overfitting, and practical applications of machine learning(5) Algorithms for variables (feature) selection(6) Bayesian Networks and learning of causal relations and structures.

6

CS-150, CS-217, CS-380

https://elearn.uoc.gr/