Learning in Rich Representations: Inductive Logic Programming and Computational Scientific Discovery

Saso Dzeroski
Joint invited talk at ICML-02 and ILP-02, Sydney, Australia
The goals of the talk were to: 
  • Review some key ideas and developments in inductive logic programming
  • Show how these ideas can be used in other learning settings, and in particular for the computational scientific discovery of quantitative laws.
  • Encourage more research on learning in rich representations, such as relational representations and differential equations, which can be used for modeling a variety of real world problems. 
 Dzeroski, S. (2002) Learning in Rich Representations: Inductive Logic Programming and Computational Scientific Discovery. In Proceedings of the Nineteenth International Conference on Machine Learning, pages 701-702. Morgan Kaufmann, San Francisco, CA. 
Abstract: [ps] [pdf]
Slides: [ps] [pdf]