ISI is restructuring its organization chart, for such reason some information is not available at the moment.


Optimization and Machine Learning methods for prevention of spreading of threats in networks

Friday, January 10, 2020

2.30 p.m

ISI Foundation 1st floor

Prof. Krzysztof Michalak (Wroclaw University of Economics)

The presentation concerns the use of computational methods for finding good solutions to problems in which the goal is to prevent the spreading of a threat in a network. The presentation discusses metaheuristic methods such as evolutionary algorithms, estimation of distribution algorithms and others. Presented algorithmic approaches include multiobjective optimization algorithms, multipopulation methods and the use of machine learning in optimization. The latter approach is based, among others, on informed genetic operators in which an ML model is used to guide the search in an evolutionary algorithm, and surrogate-based evaluation. Application areas include abstract optimization problems, such as the Firefighter Problem and numerous practical problems such as epidemics control and reduction of systemic risk in financial systems.

Krzysztof Michalak received the M. Sc. Eng. degree in computer science in 2001 and the Ph.D. degree in 2010, both from the Wroclaw University of Science and Technology. Currently, he is an assistant professor at the Wroclaw University of Economics. To date, he published more than 50 journal and conference papers. His research interests include metaheuristic algorithms, machine learning, knowledge-based optimization, and real-world applications. Currently, dr Michalak leads a project on knowledge-based optimization in which new methods are sought for utilizing the know-how of domain experts in order to improve optimization methods. He also works on the application of optimization methods to the control of animal diseases in cooperation with a team from the University of Torino.