Students will learn about concepts, techniques and selected examples of the application of soft computing. The student should be able to identify real-world problems that can be solved using soft computing techniques and be able to apply adequate techniques for solving these problems. The course focuses on the application of soft computing techniques on analyzing and processing complex data, such as images and sound.

The acquired knowledge is the basis for solving complex problems which require intelligence and cannot be explained by using conventional mathematical approaches. During this course, the student gains the basic knowledge of machine learning techniques and problems in this field. The course focuses on teaching the students how to process and represent complex data (images, and sound) in the form suitable for application of machine learning techniques.

(1) Machine Learning basics: basic concepts and problems; basic models; model evaluation (2) Neural Networks: basic model and architectures; Convolutional Neural Networks, CNN (CNN architectures, feature visualization, Deep Learning Software) (3) Digital image analysis: Clustering (K-means, distance measures - "soft" comparison of text, images and objects, image segmentation by clustering); Image preprocessing and feature extraction (simple operations - addition, subtraction, affine transformations, histogram, morphological operations, and convolution; Edge detection; Hough transform); Object detection on images ("classical" approach - feature extraction and subsequent training of a machine learning model; CNN object detection) (4) Digital sound: Fourier transformation.

Lectures, laboratory exercises, and consultations. The main focus of the course is developing the course project. The students propose the real-world problem from the field of soft computing they would like to work on, as well as the reasonable methodology for its tackling. If the student is not able to propose the problem on his own, he or she will be given a predefined project for fewer points. Students are awarded points for attending the laboratory exercises. Also, on the laboratory exercises, they are given graded optional assignments. The final part of the exam is an oral exam. The final grade is formed based on points obtained by attending the laboratory exercises, solving the optional assignments, solving the course project and taking the oral exam.