Principles of Intelligent Systems (FSI-SIS)

The goal of the course is to familiarize students with the different approaches to AI, to gain an overview of the current state of knowledge, what are its main areas and how it is developing. Students will learn a deeper understanding of AI. They will learn how to design and implement AI systems to solve specific problems. They will be introduced to mathematical models and how they can be used to understand AI systems.

Students are expected to have basic knowledge of any object-oriented programming language and basic knowledge of English language for this course.

Artificial intelligence (AI) has been one of the fastest-growing areas of computer science in recent decades, and it is becoming essential to be familiar with the basic knowledge and skills of using it. In this subject, we want to go further and show how, in some cases, to control the mind of the machine from the perspective of understanding mathematical definitions. The subject of Artificial Intelligence provides students with basic and advanced knowledge in this field. Students will be introduced to different approaches to AI, including machine learning, natural language processing, and computer vision. They will learn how to design and implement AI systems, including a description of mathematical models from selected areas.

Assessment of the course consists of points for the semester project (70 %) and points for independent tasks during the semester (30 %). The condition for awarding credit is obtaining at least 50 % of the points for the semester project. Special evaluation can be obtained for active contribution to the teaching.

Attendance at lectures is desirable, attendance at exercises is compulsory. The method of compensation for missed classes is fully within the competence of the teacher.

1. Introduction to Artificial Intelligence


2. History and current state-of-art


3. Areas of artificial intelligence


4. Machine learning


5. Neural networks


6. Causal inference principles


7. Transformers


8. Natural language processing and large language models


9. Methods for improving LLMs


10. Chatbots


11. Commercial tools and their use in practice


12. Challenges of using artificial intelligence


13. Lecturer's reserve

The PC labs are focused on the practical understanding of the material covered in the lecture topics. The emphasis is placed on the ability to work independently, i.e. on solving tasks using AI and using interactive AI tools.

1. Python and libraries for using AI tools

2. - 10. Introduction to interactive AI applications, tasks solving 

11. Creation of a chatbot

12. - 13. Work on a semester project, consultations

MOHRI, M., ROSTAMIZADEH, A., TALWALKAR, A. Foundations of machine learning. Cambridge: MIT Press, 2012. ISBN 9780262018258.

DA SILVA, I. N. Artificial Neural Networks. Cham: Springer Nature, 2016. ISBN 9783319431628. Dostupné online z: https://doi.org/10.1007/978-3-319-43162-8.

LIU, A. C. C. a LAW, O. M. K. Artificial intelligence hardware design: challenges and solutions. Hoboken: Wiley, 2021. ISBN 978-1-119-81045-2.

TUNSTALL, L., WERRA, L., WOLF, T. a GÉRON, A. Natural language processing with transformers: building language applications with Hugging Face. Revised edition. Beijing: O'Reilly, 2022. ISBN 9781098136796.

ROTHMAN, D. a GULLI, A. Transformers for natural language processing: build, train, and fine-tune deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, and GPT-3. Second edition. Birmingham: Packt, 2022. ISBN 978-1-80324-733-5.

SCHÖLKOPF, B., JANZING, D. a PETERS, J. Elements of Causal Inference: Foundations and Learning Algorithms. 1. Cambridge: The MIT Press, 2017. ISBN 0262037319. Dostupné online.

KUBLIK, S. a SABOO, S. GPT-3: building innovative NLP products using large language models. Sebastopol: O´Reilly, 2022. ISBN 978-1-098-11362-9.

PECINOVSKÝ, Rudolf. Začínáme programovat v jazyku Python. 2. přepracované a rozšířené vydání. Praha: Grada Publishing, 2022. ISBN 978-80-271-3609-4.