Course: null

» List of faculties » PRF » KMA
Course title -
Course code KMA/DEEP
Organizational form of instruction Lecture + Exercise
Level of course Master
Year of study not specified
Semester Winter
Number of ECTS credits 5
Language of instruction Czech
Status of course Compulsory, Compulsory-optional
Form of instruction Face-to-face
Work placements This is not an internship
Recommended optional programme components None
Lecturer(s)
  • Pavlačka Ondřej, RNDr. Ph.D.
Course content
1. Ensemble Learning: Core concepts, parallel techniques (voting, bagging), sequential techniques (boosting methods, gradient boosting methods). 2. Introduction to Deep Learning: Feedforward Artificial Neural Networks (Multi-Layer Perceptron, MLP) and the Backpropagation algorithm. 3. Optimization Methods and Regularization in Deep Learning. 4. Convolutional Neural Networks (CNNs): Advanced architectures (ResNet, ...), Transfer Learning. 5. Sequential Data Processing: Recurrent Neural Networks (RNNs). 6. Handling Long-Term Dependencies: LSTM and GRU architectures. 7. Attention Mechanism and the Query-Key-Value formalism. 8. Transformer Architecture and modern Large Language Models (LLMs). 9. Deep Generative Models: Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). 10. Reinforcement Learning and Deep Q-Networks (DQN).

Learning activities and teaching methods
Lecture, Dialogic Lecture (Discussion, Dialog, Brainstorming), Demonstration, Projection (static, dynamic)
Learning outcomes
The objective of the course is to develop students' ability to independently design, implement, and critically evaluate advanced machine learning models and deep neural networks, to understand the principles of generative modeling and reinforcement learning, and to understand the inner workings of modern Large Language Models (LLMs).
Understanding of advanced machine learning methods and deep neural network architectures. Ability to actively implement, optimize, and critically evaluate complex models. Understanding of the principles of generative modeling, reinforcement learning, and the inner workings of LLMs.
Prerequisites
linear algebra, calculus, programming, English language

Assessment methods and criteria
Mark, Oral exam, Student performance, Seminar Work

Course Credit: Independent completion of assigned tasks in machine learning and deep learning. Exam: Oral exam.
Recommended literature
  • Bishop, Ch.M., Bishop, H. (2024). Deep Learning: Foundations and Concepts.
  • Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. Sebastopol.
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  • Hastie, T., Tibshirani, R., Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction.
  • Higham, C. F., Higham, D. J. (2019). Deep Learning: An Introduction for Applied Mathematicians.
  • Chollet, F. (2021). Deep Learning with Python.
  • Murphy, K. P. (2023). Probabilistic Machine Learning: Advanced Topics.
  • Prince, S. J. (2023). Understanding Deep Learning.
  • Sutton, R. S., Barto, A. G. (2018). Reinforcement Learning: An Introduction.
  • Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2023). Dive into Deep Learning.


Study plans that include the course
Faculty Study plan (Version) Category of Branch/Specialization Recommended year of study Recommended semester
Faculty: Faculty of Science Study plan (Version): Mathematics (2026) Category: Mathematics courses 1 Recommended year of study:1, Recommended semester: Winter