This course aims to introduce students to modern state of Machine Learning and Artificial Intelligence. It is designed to take one year (two terms at MIPT) - approximately 2 * 15 lectures and seminars.
All learning materials are available here, full list of topics considered in the course are listed in program_*.pdf files
Organizational information about current launches available at ml-mipt.github.io
- on
masterbranch previous term materials are stored to give a quick and comprehensive overview - on
basicandadvancedbranches materials for current launches are being published - tags (e.g.
spring_2019) contain previous launches materials for convenience
- basic track (Spring 2020, updated):
lectures youtube playlist (ru),practice sessions youtube playlist (ru) - advanced track (Fall 2019):
lectures youtube playlist (ru),practice sessions youtube playlist (ru) - basic track (Spring 2019):
lectures youtube playlist (ru)
We are expecting our students to have a basic knowlege of:
- calculus, especially matrix calculus, differentiation
- linear algebra
- probability theory and statistics
- programming, especially on Python
Although if you don't have any of this, you could substitude it with your diligence because the course provides additional materials to study requirements yourself.
Informal "aggregation" of all topics by previous years students: file (in Russian) - useful for fast and furious exam passing
Also lectures and seminars contains references to more detailed materials on topics
Using docker for tasks evaluation is a good idea, prebuilt image is under cunstruction