BMETE15MF75

Course data
Course name: Artificial Intelligence in Data Science
Neptun ID: BMETE15MF75
Responsible teacher: János Török
Programme: Courses for Physicist MSc students
Course data sheet: BMETE15MF75
Requirements, Information

Information

Actualities

  • Please note that the course relies on the fact that everybody has good knowledge of python especially numpy.
  • I will use two different systems to communicate with you:
    • neptun: most official, final notes, important and prompt messages
    • moodle: materials, assignments, evaluation. For final grade use the formula below and not the one moodle supplies.
    • Please note, that I do not use microsoft teams on a daily basis, so please, do not use the chat system of the teams to communicate with me. If you have any question write an email to me torok.janos (at) ttk.bme.hu.

Teacher

​

Moodle

  • The faculty moodle system is located at https://edu.ttk.bme.hu/.
  • You are supposed to form pairs as all work is done in pairs

Subjects covered

Aim

Introduction to machine learning from a physicist's perspective, with the aim to understand how it works and less emphasis on tricks or parameter optimization

Subjects

(order may change)

  1. Deep learning (from scratch in numpy), Higher level implementations (tensorflow, sklearn, keras)
  2. Convolutional neural networks
  3. Image segmentation
  4. Pre-trained models, big models
  5. Data augmentation, auto-encoders
  6. Diffusion models
  7. Genetic algorithm
  8. Q learning, reinforcement learning
  9. LSTM networks
  10. Textual data
  11. Attention modules
  12. Unsupervised learning

Requirements

  • Two projects one fixed one of your own choice
  • Classwork solution with hard deadlines 70%
  • Test at the end of the semester

Evaluation

  • Practice solutions (pair): occasional varying number of points (extra points!)
  • Projects: 100 points each
  • Test: 40 points
  • Marks (all points summed up):
    1. -109
    2. 110-139
    3. 140-169
    4. 170-199
    5. 200-

Consultation

During the classes or on demand by email.

Old materials

Last modified: 05.09.2025