Vabljeni na naslednje v seriji SLAIS predavanj. Predavatelja Tome Emfimov in Peter Korošec bosta predstavila svojo knjigo Deep Statistical Comparison for Meta-heuristic Stochastic Optimization Algorithms, ki je pred kratkim izšla pri založbi Springer.
Predavanje bo v četrtek 19. 1. 2023 ob 13h, Oranžna soba IJS (2. nadstropje Glavne stavbe Instituta “Jožef Stefan”, Jamova 39, Ljubljana).
Povzetek:
The talk will present a recently published Springer book “Deep Statistical Comparison for Meta-heuristic Stochastic Optimization Algorithms”. The book is focused on methodologies for performing robust statistical performance assessment of meta-heuristics. The presentation will not go into mathematical and statistical details, which are presented in the book, but focus on presenting main issues that are commonly presented and overlooked when algorithm performance is analyzed and how they can be solved using Deep Statistical Comparison approach. The applicability of the approach will be shown on statistical analyses performed using single-objective and multi-objective optimization data. At the end of the presentation, a web-service-based e-learning tool (DSCTool) will be presented that provides users with all the functionalities needed to make robust statistical comparison analyses in various statistical and application scenarios.
Predavatelja:
Tome Eftimov is a researcher at the Computer Systems Department at the Jožef Stefan Institute. He is an assistant professor at the Faculty of Computer and Information Science, University of Ljubljana, and visiting assistant professor at the Faculty of Computer Science and Engineering, Ss. Cyril and Methodius University, Skopje. He obtained his PhD in Information and Communication Technologies (2018). He was a postdoctoral research fellow at Stanford University, USA (2019). In addition, he was a research associate at the University of California, San Francisco (2019). His research interests include statistical data analysis, metalearning, metaheuristics, natural language processing, representation learning, and machine learning. He has led an ARRS postdoc project (2019-2021) and currently is leading an ARRS ERC StG complementary scheme (2022-2024), ARRS bilateral project with France (2023 – 2025), and ARRS bilateral project with Germany (2023 – 2025). He was also a Scientific Coordinator of a European Food Safety Authority (EFSA)-funded project (2021 – 2022) and task leader of several H2020 and HE projects.
Peter Korošec received his PhD degree from the Jožef Stefan Postgraduate School, Ljubljana, Slovenia. Since 2002 he has been a researcher at the Computer Systems Department of the Jožef Stefan Institute, Ljubljana. He has participated in the organization of various conferences workshops as program chair or organizer. He has successfully applied his optimization approaches to several real-world problems in engineering. Recently, he has focused on better understanding optimization algorithms so that they can be more efficiently selected and applied to real-world problems. He has been leading several industrial, ARRS, and international projects.
