Description

The objective of this course is to comprehensively present the knowledge about the development of intelligent systems with machine learning, and to train students for state-of-the-art machine learning approaches used in science and industry.

Requirements

None

Instructors

red. prof. dr. VILI PODGORELEC

Contents

• Introduction: data science, artificial intelligence and machine learning, fields of use, software tools and frameworks.
• Intelligent information solutions: programming from scratch, integrated solutions for data scientists, machine learning as a service. 
• Machine learning process: basic methods and tasks, data collection and processing, feature selection, transformation and feature creation, evaluation of knowledge models. 
• Ensemble methods: combining machine learning methods, bagging, boosting, stacking, Random Forests, Gradient Boosting.
• Deep learning and neural networks, convolutional neural networks, recurrent neural networks, autoencoders, generative adversarial networks. 
• Setting and optimization of machine learning parameters. 
• Arranging machine learning projects. 
• Case studies of efficient intelligent solutions from various domains.

Learning Outcomes

On completion of this course the student will be able to 

• understand the applicability of various machine learning methods, 
• choose and use the appropriate machine learning method and prepare the data to solve a given task, 
• use ensemble methods and neural networks to solve real-world problems, 
• properly set and optimize machine learning parameters, 
• plan, perform and lead an intelligent solution development project, 
• analyse and evaluate specific intelligent solutions and/or machine learning based systems.

Planned Activities

• lectures, 
• case studies, 
• computer tutorials, 
• project.

Assessment Methods and Criteria

• Written examination: 50%
• Computer skills: 40%
• Practical exam: 10%