FIT CTU Course Pages
NI-AML — Advanced machine learning
Go to course navigation

Schedule and Materials

The course introduces students to selected advanced topics of machine learning and artificial intelligence. The topics present techniques in the field of recommendation systems, image processing, control and interconnection of physical laws with the field of machine learning. The aim of the exercise is to familiarize students with the methods discussed.

Lectures

WeekDateLecturerTopic & Materials
119.02.2026+LRodrigo da Silva Alves
226.02.2026Rodrigo da Silva Alves
  • Lecture: Recommender Systems (2)
305.03.2026+LMiroslav Čepek

HOMEWORK

  1. Measure and study the influence of quantisation on speed and quality of answers. Define 5 questions and use them as benchmark. Use smaller models (Qwen 3B, Mistral 7B, …​). Create a table mapping influence of quantisation strength on inference speed and on a quality metrics (ROUGE or similar).
  2. Explore influence of QLoRA parameters (rank, alpha, dropout) on finetuning results. Find a small testing dataset and explore influence of parameters on validation loss, quality metrics. Show examples demonstrating differences in finetuning.

Please submit your homework to Miroslav’s email (miroslav.cepek@fit[…]) with the subject line [NI-AML26]_your_kos_login. Due: 05/04/2026.

412.03.2026Miroslav Čepek* Lecture: Large Language Models
519.03.2026+LZdeněk Buk
626.03.2026Vojtech Vancura
  • Lecture: Sparse (deep) Machine Learning
702.04.2026+LCenek Zid
809.04.2026Miroslav Čepek
916.04.2026+LVojtěch Rybář
1023.04.2026Vojtěch Rybář
1130.04.2026EXCEPTION
  • No lecture
1207.05.2026Matej Jech
  • Lecture: TBA
1314.05.2026+LMiroslav Čepek
  • Lecture: Project Presentation
  • Tutorial: Project Presentation