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, Informations

Information

Actualities

  • The course will be held in person. The first course on 8th of September will also be given. Since this is only an introductory course and last year I recorded all lectures those who cannot attend this lecture in person can watch the corresponding video.
  • Please note that the course relies on the fact that everybody has good knowledge of python especially numpy.
  • I will use four different systems to communicate with you (sorry):
    • neptun: most official, final notes, important and prompt messages
    • moodle: submit everything here, evaluation will also take place here. For final grade use the formula below and not the one moodle supplies.
    • physics.bme.hu: the official institute webpage, requirements are posted here. Lectures and homeworks are posted here.
    • Microsoft teams: Lectures were recorded and I can give access upon request
    • 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 can log in using your university id. Courses should appear soon. All works must be submitted using the moodle system.
  • You are supposed to make pairs, homeworks are individual, but the practice work, data challenge and the final projects are supposed to be group works.

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 oprimization

Subjects

(order may change)

  1. Image segmentation
  2. Decision tree
  3. Deep learning (from scratch in numpy)
  4. Higher level implementations (tensorflow, sklearn, keras)
  5. Convolutional neural networks
  6. Pre-trained models
  7. Data augmentation
  8. Textual data
  9. LSTM networks
  10. Reinforcement learning

Requirements

  • 50% homework
  • Project presented and accepted

Evaluation

  • Homeworks (individual): 100 points/HW
  • Practice solutions (pair): occasional varying number of points (extra points!)
  • Data challenge (pair): 500 points
  • Project and its presentation (pair): 1000 points
  • Marks:
    1. -1099
    2. 1100-1399
    3. 1400-1699
    4. 1700-1999
    5. 2000-

Results

  • In moodle

Homework

  1. In the moodle

Classes

  1. ea01.pdf, class01.zip
  2. ea02.pdf, class02.zip
  3. ea03.pdf, class03.zip
  4. ea4.pdf, class04.zip
  5. ea05.pdf, class05.zip The extra practice course (by Axel Katona) ea05b.pdf, class05b.zip
  6. ea06.pdf, class06.zip
  7. ea07.pdf, class07.zip
  8. ea08.pdf, class08.zip
  9. ea09.pdf, class09.zip
  10. ea10.pdf, class10.zip
  11. ea11.pdf, class11.zip
  12. ea12.pdf, class12.zip

Old materials

Last modified: 30.08.2022