Navigation

26D111VID - Artificial Intelligence and Deep Learning

Course specification
Course title Artificial Intelligence and Deep Learning
Acronym 26D111VID
Study programme Electrical Engineering and Computing
Module Computer Engineering and Informatics
Type of study doctoral studies
Lecturer (for classes)
Lecturer/Associate (for practice)
    Lecturer/Associate (for OTC)
      ESPB 9.0 Status elective
      Condition
      The goal Introduce students to the methodologies and applications of modern development in artificial intelligence area, with an emphasis on advanced technologies.
      The outcome The course will cover modern types of neural networks, hyperparameter tuning and optimization, as well as the use of various tools. The main outcome is to acquire the skills and methods needed to solve complex AI problems students may encounter in real-world scenarios, and to apply the most appropriate and effective approach based on their knowledge.
      Contents
      Contents of lectures Advanced deep learning techniques. Analysis of advanced neural network design methods, including optimization, hyperparameter tuning, and deep learning frameworks. Recurrent neural networks, their applications, and related methods. Transformers—their foundations, concepts, and applications—including transformer-based language models. Examples from industry and the academic community.
      Contents of exercises Analysis and solution of practical tasks, demonstrating how to address specific problems using artificial intelligence and deep learning techniques. Practical examples with development tools applied to various datasets.
      Literature
      1. Deep Learning – Ian Goodfellow, Yoshua Bengio, Aaron Courville (MIT Press) (Original title)
      2. Pattern Recognition and Machine Learning – Christopher M. Bishop (Springer) (Original title)
      3. Machine Learning: A Probabilistic Perspective – Kevin Murphy (MIT Press) (Original title)
      Number of hours per week during the semester/trimester/year
      Lectures Exercises OTC Study and Research Other classes
      8
      Methods of teaching Presentation, individual work, discussion
      Knowledge score (maximum points 100)
      Pre obligations Points Final exam Points
      Activites during lectures 0 Test paper 0
      Practical lessons 0 Oral examination 30
      Projects 70
      Colloquia 0
      Seminars 0