Pattern recognition

Subject description

Within this course, students delve into advanced pattern recognition methods, including speech and other audio signals, computer images, and multimodal data. They are introduced to the mathematical foundations essential for understanding and implementing pattern recognition algorithms. The focus is on deep learning and neural network architectures, where students familiarize themselves with advanced models such as convolutional and recurrent neural networks, and explore new trends in deep machine learning methods. The course also covers practical applications of pattern recognition methods in industry and research, with case studies from various fields. Ethical and responsible use of pattern recognition technologies is addressed, emphasizing issues of privacy, bias, and decision automation. Special attention is also given to testing pattern recognizers and appropriately evaluating the probability of recognition errors.

The subject is taught in programs

Objectives and competences

To acquaint students with the advanced mathematical and computational approaches to pattern recognition by classification and analysis.

Teaching and learning methods

lectures,
individual consultations,
seminar projects.

Expected study results

After completion of the course the student will be able to demonstrate knowledge and understanding of:

developing systems based on recognition of external signals,
modelling rational capabilities of human beings (e.g. perception and cognition of the environment, learning),
state-of-the-art methods for pattern segmentation, feature extraction, clustering and classification.

During the course the student will gain and improve transferable skills such as:

use of information technology: the use of development tools (OpenCV, Weka, Orange, scikit-learn, PyTorch), programming environments (Matlab, Netbeans, Visual Studio Code, PyCharm), programming languages (Matlab, C++, Java, Python); and
problem solving: problem analysis, algorithm design, implementation and testing of a program.

Basic sources and literature

N. Pavešić: Razpoznavanje vzorcev : uvod v analizo in razumevanje vidnih in slušnih signalov,  3. popravljena in dopolnjena izdaja,  Založba FE in FRI, 2012. ISBN 978-961-243-201-0. [COBISS.SI-ID 260256256]
M. Bishop, Christopher.: Pattern recognition and machine learning, 8. popravljena izdaja, Springer, 2009. ISBN 0-387-31073-8. [COBISS.SI-ID 7988308]
R. C. Gonzalez, R. E. Woods: Digital Image Processing, Pearson, 2018. ISBN 978-1-292-22304-9. [COBISS.SI-ID – 12389972]