Description

The student will learn methods of intelligent system design, implementation and use focused on modern machine learning techniques.

Requirements

Recommended are Basic skills in machine learning and artificial intelligence.

Instructors

red. prof. dr. MILAN ZORMAN

Contents

• Concepts of intelligent system design. 
• Applications of IS 
• Implementation of IS components in modern tools (e.g. ‘R’) 
• Data acquisition for IS 
• Infrastructure for intelligent systems. 

• Advanced knowledge representations and machine learning techniques: 

  o Symbol-based methods, 

  o Connectivist methods, 

  o Association rules, 

  o Bayes classifiers, 

  o Hybrid methods. 

• Transition from classic connectivist methods to deep learning 
• Upgrading knowledge models 
• Prediction in dynamic systems and chaos theory. 
• Cellular automata. 
• Nature-based intelligent systems. 
• Evaluation, ethical questions and challenges. 
• Functional safety for IS

Learning Outcomes

• Present the knowledge of advanced techniques of intelligent system design, implementation and evaluation, 
• Understane the safety concept in intelligent systems, 
• Use computer tools for data preparation, 
• Analyse the results of use of intelligent systems, 
• Use the knowledge of intelligent systems for more efficient problem solving

Planned Activities

• lectures, 
• lab work.

Assessment Methods and Criteria

• Written examination: 50%
• Laboratory work: 50%