On Applying Surrogates in Evolutionary (Multi-Objective) Optimisation

☰ Meni

V ponedeljek, 8. maja 2017, bo ob 16.00 uri v prostorih Fakultete za matematiko, naravoslovje in informacijske tehnologije Univerze na Primorskem, Glagoljaška 8, Koper predavanje v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM.

PLACE: FAMNIT-1-MP2 ob 16:00

———————————————————-

LECTURER: prof. Boris Naujoks

———————————————————-

TITLE: On Applying Surrogates in Evolutionary (Multi-Objective) Optimisation

———————————————————-

ABSTRACT:
The presentation will start with a short introduction to evolutionary algorithms (EA) and the concepts of Pareto-based multi-objective optimisation that are often applied in EA. The industrial applicability of EA is often said to be limited by the runtime of the algorithm, which itself is heavily depending on the time spent for single fitness function evaluations. For this scenario, the method of learning and incorporating surrogate models became a state-of-the-art during the last decade. To introduce surrogate-assisted EA, we first focus on different modelling techniques that were applied frequently. After that, we look at different techniques on how to integrate surrogates into EA and discuss typical problems arising when implementing these in real-world optimisation tasks. The talk will conclude with a discussion of open issues.

BIO:
Boris Naujoks is a professor for Applied Mathematics at TH Köln – Cologne University of Applied Sciences (CUAS). He joined CUAs after he received his PhD from Dortmund Technical University. During his time in Dortmund, in the group of Hans-Paul Schwefel, Boris worked as a research assistant in different projects and, additionally, gained industrial experience working for different SMEs. Meanwhile, he enjoys the combination of teaching mathematics as well as computer science and exploring EC and CI techniques at the Campus Gummersbach of CUAS. He focuses on multi-objective (evolutionary) optimisation, the integration of surrogates, and the (industrial) applicability of the explored methods.

Predavanje je organizirano v okviru PONEDELJKOVEGA SEMINARJA RAČUNALNIŠTVA IN INFORMATIKE Oddelkov za Informacijske znanosti in tehnologije UP FAMNIT in UP IAM ter SYNERGY – H2020 TWINNING projekta.

Vabljeni!