Evidence Theory with Applications
This course aims to introduce the evidence theory (also referred to as Dempster-Shafer theory, or theory of belief functions), a formalism for reasoning with uncertainty, and its application in decision making and machine learning. It will first introduce the fundamental concepts and operations of the evidence theory, including belief functions and operators for evidence combination, and then discuss its applications in the problem of decision making under uncertainty and information fusion for ensemble learning.
Upon the completion of this course, students will not only familiarize with the basic concepts of the evidence theory as a tool for modeling and reasoning with uncertainty but also hopefully be able to develop evidence theory-based thinking and approach for application in their own research.
Class schedule:
- 30/08/2024, room B112
- 04/09/2024, seminar room
- 05/09/2024, seminar room
- 10/09/2024, room B112