Evolutionary Algorithms with Applications

Friday, November 23, 2012 to Wednesday, November 28, 2012

 

Infotech Oulu Doctoral Program

Evolutionary Algorithms with Applications

Lecturer: Professor Bogdan Filipič, Department of Intelligent Systems, Jožef Stefan Institute, Ljubljana, Slovenia, Email: bogdan.filipic(at)ijs.si

Duration: 10 hours

Schedule:

fri  23.11 at 10-12,   TF105
mon 26.11 at 9-12,   TF105
tue  27.11 at 9-12,  SÄ112
wed  28.11 at 10-12, TF105

Grading: Students attending the course and passing the assignment will be entitled to receive two credit points.

More information: erkki.laitinen(at)oulu.fi

Objectives

  • To present the motivation for and basic concepts of evolutionary computation

  • To introduce various types of evolutionary algorithms and their characteristics

  • To teach the participants how to apply the methodology to search and optimization problems and how to evaluate the results

Contents

  • Evolutionary computation as a biologically inspired search and optimization methodology

  • Elements of evolutionary algorithm design: iterative population-based search, representation of solutions, fitnes measure, operators, algorithm parameters and their tuning, termination criterion

  • Types of evolutionary algorithms: genetic algorithms, evolution strategies, evolutionary programming, genetic programming, differential evolution

  • Evaluation of results: statistical approach and performance measures

  • Applied issues: algorithm hybridization, multi-objective and dynamic optimization, optimization with subjective evaluation of solutions

  • Case studies from real-world problem solving with evolutionary algorithms: process parameter optimization, production scheduling

Literature

A. E. Eiben, J. E. Smith. Introduction to Evolutionary Computing. Corrected 2nd printing. Springer, Berlin, 2007.

B. Filipič. Evolutionary production scheduling in car manufacture. In: B. Filipič, J. Šilc (Eds.), Proceedings of the International Conference on Bioinspired Optimization Methods and their Applications  BIOMA 2004, Ljubljana, Slovenia,  pp. 127–136. Jožef Stefan Institute, Ljubljana, 2004.

B. Filipič, E. Laitinen. Model-based tuning of process parameters for steady-state steel casting. Informatica, 29 (4): 491–496, 2005.

P. Siarry, Z. Michalewicz (Eds.).  Advances in Metaheuristics for Hard Optimization. Springer, Berlin, 2008.

About the lecturer

Bogdan Filipič received his Ph.D. in Computer Science from the University of Ljubljana, Slovenia, in 1993, and is now a senior research associate at the Department of Intelligent Systems of the Jožef Stefan Institute, Ljubljana, and an associate professor of Computer and Information Science at the University of Ljubljana. His research interests include stochastic optimization, evolutionary computation, and intelligent data analysis. He published extensively in international scientific journals and was a principle investigator in national and international projects dealing with information technology for production processes optimization, energy efficiency, and cultural heritage preservation. His previous collaboration with the University of Oulu includes participation in the multilateral project COST 526 (2001–2005) and three Slovenian-Finnish projects (2004–2006, 2009–2010, 2011–2012). He was giving courses at Infotech Oulu in 2005, 2006 and 2007.

Add to calendar

Back to events

Last updated: 30.10.2012