Lecture
SAILS Lunch Time Seminar: Matthijs van Leeuwen
- Date
- Monday 6 November 2023
- Time
- Location
- Online only
Learning Explainable Models through Compression
Whenever you have learned something from data, you have implicitly also compressed the data. In this talk we explore how we can turn this observation around and use compression to learn explainable models from data. To this end we look at how we can model and quantify information in data in an interpretable manner, and how we can use this for data mining and machine learning.
Without diving into the details, I briefly explain the theoretical foundations, i.e., Kolmogorov complexity and the minimum description length (MDL) principle. After that I will showcase some examples, among which a use case on predicting re-admission of patients to the intensive care unit, a problem in health care we investigate in collaboration with the LUMC. The examples demonstrate that our approach has desirable properties, i.e., the resulting models are interpretable, generalise well even when relatively little data is available, and no 'magic' or supercomputers are needed to learn them.
Join us!
The SAILS Lunch Time Seminar is an online event, but it is not publicly accessible in real-time. Please click the the link below to register to our mailinglist and receive participation links for our Lunch Time Seminars.
Click here to register!