460-2078/02 – Fundamentals of Artificial Intelligence (ZUI)
| Gurantor department | Department of Computer Science | Credits | 3 |
| Subject guarantor | prof. Ing. Roman Šenkeřík, Ph.D., DBA | Subject version guarantor | prof. Ing. Roman Šenkeřík, Ph.D., DBA |
| Study level | undergraduate or graduate | Requirement | Optional |
| Year | 3 | Semester | summer |
| | Study language | English |
| Year of introduction | 2024/2025 | Year of cancellation | |
| Intended for the faculties | FEI | Intended for study types | Bachelor |
Subject aims expressed by acquired skills and competences
The aim of the course is to introduce students to the basics of theory and practical applications of artificial intelligence (AI). The aim is to acquire the following knowledge. The student will define and differentiate between types of machine learning (supervised, unsupervised, reinforcement) and explain basic terminology including neural network architectures and practical applications. The student will list and define key techniques and models used in NLP (natural language processing), including transformer models such as BERT and GPT. The student will give examples of generative models, and explain their principles and applications. The student will analyze how AI contributes in conflict resolution, optimization, and decision making, and will establish the importance of interpretability of AI models and describe methods for improving transparency and visualization. The goal is to acquire the following skills: the student will design and implement basic machine learning algorithms for simple applications. The student will build and train a basic neural network to solve a specific problem. The student will use generative modeling techniques to solve a practical problem or to create a simple application, such as a chatbot. The student will analyze data and use tools to improve the understanding and interpretability of AI models.
Teaching methods
Lectures
Tutorials
Project work
Summary
The course should provide students with a solid foundation in the theory and practical applications of AI, covering the history, key concepts, algorithms, examples of the use of generative AI, overlap and connections with robotics, game theory, cognitive science, and finally, clearly define the importance of data interpretability, and issues of future development and ethical aspects of AI.
Compulsory literature:
Recommended literature:
Way of continuous check of knowledge in the course of semester
Submission of continuous assignments completed in the exercises, alternatively one main project assignment. Completion of a final exam.
E-learning
Other requirements
There are no other requirements imposed on the student.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
1. Introduction to Artificial Intelligence (AI)
- History and development of AI
- Definitions and areas of AI (machine learning, deep learning, robotics, natural language processing, etc.)
- Overview of real-world applications of AI
2. Foundations of machine learning
- Overview of types of machine learning: supervised, unsupervised, reinforcement
- Basic concepts and terminology
- Simple machine learning algorithms and their applications
3. Brief background on neural networks, deep learning and applications
- Basic terminology of neural networks.
- Brief overview of architectures, perceptron, multilayer perceptrons, also deep neural networks and their architectures (CNN, RNN, LSTM)
- Applications of deep learning
4. Natural Language Processing (NLP)
- Introduction to NLP and its applications (chatbots, automatic machine translation)
- NLP techniques and models (tokenization, word embeddings, transformer models)
- Introduction to BERT and GPT models (transformer architectures)
5. Generative models in AI
- Introduction to generative models and their principles
- Generative adversarial networks (GANs) and their applications
6. Generative models in AI II
- Generative AI in software engineering and technical fields
- Examples of the use of generative AI in graphics, design and other fields
7. AI and game theory, cognitive systems and artificial life, robotics
- Game theory and its relation to AI
- Application of game theory in AI for conflict resolution, optimization and decision making (business strategy, social simulation)
- Foundations of cognitive systems and their inspiration by human thinking, relation to AI
- Introduction to artificial life (Alife) and its goals: simulation of life using AI, examples of Alife projects.
- Robotics and its integration with AI, swarm intelligence
8. Decision systems and optimization
- Introduction to decision systems and optimization algorithms in AI
- Examples of applications in logistics and planning
- AI in dynamic environments
9. Data visualization and interpretability
- What is Explainable Artificial Intelligence (XAI)
- The importance of interpretability of AI models (white box/glass box/black box)
- Examples of tools and methods to improve transparency and visualization to better understand data and model results
10 The future of AI, ethics and societal implications of AI
- Trends and challenges in AI
- Possible developments and directions for AI in the coming years
- Ethical dilemmas (autonomous systems, surveillance)
- Bias and fairness in algorithms
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction
Předmět neobsahuje žádné hodnocení.