The importance of Parameter Control in Evolutionary Computation

Sažetak/Abstract:

One of the challenges in optimization approaches with evolutionary algorithms is the proper selection of the control parameters. The control parameters allow to adjust the behaviour of the algorithms to the problem at hand. Several control parameters need to be set for a successful search of the optimum of an objective function. Typical control parameters are the population size, the mutation strength, the crossover rate, the selective pressure, etc. The choice of these parameters can have a significant impact on the performance of the algorithm and need thus to be executed with care. With parameter control approach no prior training of parameters is needed. Also, the optimal parameter values change during the optimization process: e.g., at the beginning of an optimization process we typically aim for exploration, while in the later stages we want the algorithm to converge and to focus its search on the most promising regions in the search space. To present the importance of the dynamic setting of control parameters some basic theoretical aspects are outlined and followed by the presentation of some real-world cases of the use of parameter control.

Životopis/Curriculum Vitae:

Gregor Papa (gregor.papa@ijs.si, http://cs.ijs.si/papa/) is a Senior researcher and a Head of Computer Systems Department at the Jožef Stefan Institute, Ljubljana, Slovenia, and an Associate Professor at the Jožef Stefan International Postgraduate School, Ljubljana, Slovenia. He received the PhD degree in Electrical engineering at the University of Ljubljana, Slovenia, in 2002. Gregor Papa's research interests include meta-heuristic optimisation methods and hardware implementations of high-complexity algorithms, with a focus on dynamic setting of algorithms' control parameters. His work is published in several international journals and conference proceedings. He regularly organizes several conferences and workshops in the field of nature-inspired algorithms from the year 2004 till nowadays. He led and participated in several national and European projects. Gregor Papa is a member of the Editorial Board of the Automatika journal (Taylor & Francis) for the field “Applied Computational Intelligence”. He is a Consultant at the Slovenian Strategic research and innovation partnership for Smart cities and communities.

Pristup/Accessing info:

Due to the still ongoing CoViD-19 situation the meeting will be held solely by using on-line casting and telepresence solution. The lectures are free of charge and publicly available. Your attendance can be accomplished by visiting casting solution on following link:

https://us02web.zoom.us/j/86320838898?pwd=Nk9XM1RPejJLRWdJdkZXaVl4cjA1QT09