Many can train machine learning models, but few understand how these models work. Whenever machine learning goes wrong (and it does so frequently), only understanding can save the day. At the upcoming Data Science Seminar we will try to understand various kinds of machine learning models and discuss how to explain their predictions to non-experts.
- 17:00 - Welcoming coffee
- 17:15 - Introduction by Meelis Kull (moderator of the event)
- 17:20 - Ando Saabas (Taxify/Bolt) - Interpreting tree-based models
- 17:45 - Anna Aljanaki (Mooncascade) - What music information retrieval can tell us about Eurovision?
- 18:10 - Coffee break
- 18:30 - Kairit Sirts (University of Tartu) - Understanding neural models for text analysis
- 18:55 - Markus Lippus (MindTitan) - Trust the machine, or do you really need to know what your algorithm is doing?
- 19:20 - Panel discussion
- 19:45 - Networking
Please register to participate.
This event is supported by the University of Tartu ASTRA project PER ASPERA Doctoral School of Information and Communication Technologies.