We use cookies on this site. By browsing our site you agree to our use of cookies. Close this message Find out more

Home > Computer Science home > Events > Seminar Prof. Igor Kononenko
More in this section Events articles

Seminar Prof. Igor Kononenko

Bourne Annex 290
21/03/2017 (15:00-16:00)

Igor Kononenko

Prof. Igor Kononenko, Faculty of Computer and Information Science, University of Ljubljana, Slovenia

Explaining individual predictions of an arbitrary model

After a brief overview of our research in the field of machine learning and data mining I will present a general method for explaining individual predictions of arbitrary classification and regression models. The method is based on fundamental concepts from coalitional game theory and predictions are explained with contributions of individual feature values. All subsets of input features are perturbed, so interactions and redundancies between features are taken into account. We overcome the method’s initial exponential time complexity with a sampling-based approximation. The method is efficient and its explanations are intuitive and useful. Besides individual predictions, the method can also be used to explain the whole models.

Igor Kononenko is a professor at the Faculty of Computer and Information Science, University of Ljubljana, Slovenia. He is the Head of Laboratory for Cognitive Modelling and the Head of Artificial Intelligence Department. His major research interest is machine learning and data mining. He is the (co)author of about 225 papers in these fields and 13 textbooks, including the book published by Horwood: Machine Learning and Data Mining - Introduction to Principles and Algorithms. Kononenko is a member of editorial boards of two journals and was a PC member of more than 30 scientific conferences.


Comment on this page

Did you find the information you were looking for? Is there a broken link or content that needs updating? Let us know so we can improve the page.

Note: If you need further information or have a question that cannot be satisfied by this page, please call our switchboard on +44 (0)1784 434455.

This window will close when you submit your comment.

Add Your Feedback