Online MLMU #11: Thoth: Reinforcement learning-based dependency resolution

  Machine learning

The meetup will be hosted online - using Zoom platform and streamed on YouTube.

Dependency resolvers try to satisfy the version range requirements of libraries used using different approaches, such as backtracking or implementing an SAT solver. But what about plugging in machine learning algorithms in this AI/ML era and try to resolve software stacks using reinforcement learning? What are the benefits and drawbacks of such an approach? What is the state space imagined, what are the actions to be taken to accumulate rewards, and how to balance exploration and exploitation in the state space? Let's play this game and see who wins...

Fridolin Pokorny is a passionate Pythonista. Working on scalable platforms and machine learning applications in Red Hat’s office of the CTO.

Language: English

- Talk
- Discussion
- Networking (Zoom)

Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except for Prague, MLMU also spread to Brno, Bratislava and Košice.