Acquiring knowledge about fundamental machine learning models, algorithms, key design elements, and evaluation techniques.

After completing the course, the students understand basic machine learning techniques, they have applied them in practice, they are able to select techniques adequate for the problem at hand, they understand how the decisions made in the algorithm design phase affect the algorithm behavior, and can estimate the quality of the obtained models.

- Basic elements of learning algorithm design – model, loss function, regularization, optimization method; - Linear models (linear regression, logistic regression, multinomial logistic regression); - Large margin based classification and regression (support vector machines) - Instance based models (non-parametric probability density estimation, Nadaraya-Watson kernel methods, support vector machines with kernels); - Ensemble methods (random forests, AdaBoost, gradient boosting); - Neural networks and deep learning (fully connected neural networks, convolutional neural networks, recurrent neural networks); - Clustering (k-means, expectation maximization, etc.); - Data representation learning (autoencoders); - Generative adversarial networks; - Model evaluation and selection - Regularization; - Optimization methods.

Machine learning techniques: implementation and utilization using different data sets and tools.

None.

Total assigned hours: 90

New material: 30
Elaboration and examples (recapitulation): 0

Auditory exercises: 45
Laboratory exercises: 0
Calculation tasks: 0
Seminar paper: 0
Project: 0
Consultations: 0
Discussion/workshop: 0
Research study work: 0

Review and grading of calculation tasks: 0
Review and grading of lab reports: 0
Review and grading of seminar papers: 0
Review and grading of the project: 0
Test: 0
Test: 10
Final exam: 5

Activity during lectures: 0
Test/test: 20
Laboratory practice: 0
Calculation tasks: 0
Seminar paper: 20
Project: 0
Final exam: 60
Requirement for taking the exam (required number of points): 0

Christopher Bishop, Pattern Recognition and Machine Learning, Springer, 2006.; Kevin Murphy, Machine Learning: A Probabilistic Perspective, The MIT Press, 2012.; Trevor Hastie, Robert Tibshirani, Jerome Friedman, The Elements of Statistical Learning, Springer, 2008.; Richard Sutton, Andrew Barto, Reinforcement Learning: An Introduction, The MIT Press, 1998.; Младен Николић, Анђелка Зечевић, Машинско учење, скрипта.