The article “Metamodel-based optimization of hot rolling processes in the metal industry” (Christian Jung, Martin Zaefferer, Thomas Bartz-Beielstein, and Günter Rudolph) is available online. It is published in the “The International Journal of Advanced Manufacturing Technology”. The abstract reads as follows: Continue reading
Iain Dunning, Swati Gupta, and John Silberholz (Operations Research Center, Massachusetts Institute of Technology) state: “Though empirical testing is broadly used to evaluate heuristics, there are shortcomings with how it is often applied in practice”. Although their paper focuses on Max-Cut and Quadratic Unconstrained Binary Optimization, their ideas are interesting for other problems as well. The corresponding paper can be downloaded here.
Anyone who clicks on the link until August 24, 2016, will be taken to the final version of the article “Multi-fidelity modeling and optimization of biogas plants” (Martin Zaefferer, Daniel Gaida, Thomas Bartz-Beielstein) on ScienceDirect for free. No sign up or registration is needed – just click and read! Here is the link: http://authors.elsevier.com/a/1TK9q5aecSRzFl
Highlights of this article read as follows:
- Accurate and fast simulation models mandatory for the optimization of biogas plants.
- Improve precision of simulation models without increasing the number of evaluations.
- Combining results: complex simulator, simple estimation-based model and surrogate model.
- Advantages and limitations of multi-fidelity modeling approaches are discussed.
138 Promovierende forschen an der TH Köln. Die neue Ausgabe des Hochschulmagazins “Inside out” stellt fünf von ihnen vor – und ihre Forschungsthemen. Darunter auch Margarita Rebolledo und Jörg Stork aus dem SPOTSeven Team. Weitere Informationen unter https://www.th-koeln.de/hochschule/das-neue-inside-out-ist-da_34653.php
Springer announces this handbook as follows:
“The Springer Handbook of Computational Intelligence is the first book covering the basics, the state-of-the-art and important applications of the dynamic and rapidly expanding discipline of computational intelligence. This comprehensive handbook makes readers familiar with a broad spectrum of approaches to solve various problems in science and technology. Possible approaches include, for example, those being inspired by biology, living organisms and animate systems. Content is organized in seven parts: foundations; fuzzy logic; rough sets; evolutionary computation; neural networks; swarm intelligence and hybrid computational intelligence systems. Each Part is supervised by its own Part Editor(s) so that high-quality content as well as completeness are assured.”
Frank Neumann, Carsten Witt, Peter Merz, Carlos A. Coello Coello, Thomas Bartz-Beielstein, Oliver Schütze, Jörn Mehnen, and Günther Rail served as part editors for Evolutionary Computation”. Here is the official Springer link: http://www.springer.com/de/book/9783662435045 Continue reading
The unformatted and unedited PDF of the article “Multi-fidelity Modeling and Optimization of Biogas Plants” (Martin Zaefferer, Daniel Gaida, Thomas Bartz-Beielstein) is now available online at
Highlights of this article include
• Accurate and fast simulation models mandatory for the optimization of biogas plants
• Improve precision of simulation models without increasing the number of evaluations
• Combining results: complex simulator, simple estimation-based model & surrogate model
• Advantages and limitations of multi-fidelity modeling approaches are discussed
This report presents a practical approach to stacked generalization in surrogate model based optimization. It exemplifies the integration of stacking methods into the surrogate model building process.
First, a brief overview of the current state in surrogate model based optimization is presented. Stacked generalization is introduced as a promising ensemble surrogate modeling approach. Then two examples (the first is based on a real world application and the second on a set of artificial test functions) are presented. These examples clearly illustrate two properties of stacked generalization:
(i) combining information from two poor performing models can result in a good performing model and
(ii) even if the ensemble contains a good performing model, combining its information with information from poor performing models results in a relatively small performance decrease only.
The paper can be downloaded from https://cos.bibl.th-koeln.de/frontdoor/index/index/docId/375