Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture introduces the concept of maximum entropy inference, which is useful when partial information about data is available. The goal is to find a probability distribution that is consistent with the known information and has the least amount of extra structure. The lecture covers the optimization process to find the optimal probability distribution under given constraints, emphasizing the importance of maximizing entropy. Examples are provided to illustrate the application of maximum entropy inference in different scenarios.