Courses – Fakultet tehničkih nauka u Novom Sadu

Subject: Machine learning 2 (17.EK471)

Native organizations units: No data

Type of studies	Title

General information:

Category	Theoretical-methodological
Scientific or art field	Telecommunications and Signal Processing
Interdisciplinary	No
ECTS	6

Educational goal:

This course focuses on advanced machine learning topics with an emphasis on the theoretical foundations and the advanced implementation tools/practices. The topics go deep into specific supervised, unsupervised and semi-supervised algorithms addressing state-of-the-art machine learning techniques.

Educational outcome:

Students will be able to interpret and interrelate different advanced ML algorithms and approaches. Students will know how to approach the data, identify and select the most convenient ML approaches, regularization techniques, monitor training and adjust regularization parameters. Students will master the use of Python based toolboxes.

Course content:

Neural Networks: Introduction, architectures and training procedures, evaluation and application. Ensemble learning: Bagging and boosting. Clustering - advanced algorithms, mixture models and expectation-maximization (EM) algorithm, ensemble clustering. Semi-supervised algorithms. Hidden Markov models. Probabilistic graphical models (inference, belief propagation, practical application).

Teaching methods:

Lectures, computer lab sessions (Matlab, Python), homework, consultations, active learning, project and research based learning, workshops.

Literature:

Authors	Title	Year	Publisher	Language
Hastie, T., Tibshirani, R., Friedman, J.	The Elements of Statistical Learning : Data Mining, Inference, and Prediction	2009	Springer, New York	English
Kevin Murphy	Machine Learning: A Probabilistic Perspective	2012	MIT Press	English
Goodfellow, I., Bengio, Y., Courville, A.	Deep Learning	2017	MIT Press, Cambridge	English
Bishop, C.M.	Pattern Recognition and Machine Learning	2006	Springer, New York	English
Khanna, T.	Foundations of Neural Networks	1990	Addison-Wesley, Massachusetts	English

Knowledge evaluation:

Course activity	Pre-examination	Obligations	Number of points
Project	Yes	Yes	40.00
Homework	Yes	Yes	5.00
Written part of the exam - tasks and theory	No	Yes	50.00
Homework	Yes	Yes	5.00

Lecturers:

Asistent sa doktoratom Nosek Tijana

Assistant with PhD

Computational classes

Asistent Šobot Srđan

Assistant - Master

Computational classes

prof. dr Sečujski Milan

Full Professor

Lectures

prof. dr Lončar-Turukalo Tatjana

Full Professor

Lectures

Faculty of Technical Sciences

University of Novi Sad

Contact:

Address: Trg Dositeja Obradovića 6, 21102 Novi Sad

Phone: (+381) 21 450 810
(+381) 21 6350 413

Fax : (+381) 21 458 133
Emejl: ftndean@uns.ac.rs

Faculty of Technical Sciences

University of Novi Sad

Subject: Machine learning 2 (17.EK471)

Native organizations units: No data

Study programmes of the course:

Educational goal:

Educational outcome:

Course content:

Teaching methods:

Literature:

Knowledge evaluation:

Lecturers:

Asistent sa doktoratom Nosek Tijana

Computational classes

Asistent Šobot Srđan

Computational classes

prof. dr Sečujski Milan

Lectures

prof. dr Lončar-Turukalo Tatjana

Lectures

Faculty of Technical Sciences

University of Novi Sad

Contact: