1 code implementation • 25 Jan 2022 • Laurens Bliek, Paulo da Costa, Reza Refaei Afshar, Yingqian Zhang, Tom Catshoek, Daniël Vos, Sicco Verwer, Fynn Schmitt-Ulms, André Hottung, Tapan Shah, Meinolf Sellmann, Kevin Tierney, Carl Perreault-Lafleur, Caroline Leboeuf, Federico Bobbio, Justine Pepin, Warley Almeida Silva, Ricardo Gama, Hugo L. Fernandes, Martin Zaefferer, Manuel López-Ibáñez, Ekhine Irurozki
Overall, by organizing this competition we have introduced routing problems as an interesting problem setting for AI researchers.
no code implementations • 29 Jul 2021 • Jörg Stork, Philip Wenzel, Severin Landwein, Maria-Elena Algorri, Martin Zaefferer, Wolfgang Kusch, Martin Staubach, Thomas Bartz-Beielstein, Hartmut Köhn, Hermann Dejager, Christian Wolf
We have built a novel system for the surveillance of drinking water reservoirs using underwater sensor networks.
no code implementations • 19 Jul 2021 • Eva Bartz, Martin Zaefferer, Olaf Mersmann, Thomas Bartz-Beielstein
The R package SPOT is used to perform the actual tuning (optimization).
no code implementations • 30 May 2021 • Thomas Bartz-Beielstein, Frederik Rehbach, Amrita Sen, Martin Zaefferer
A surrogate model based hyperparameter tuning approach for deep learning is presented.
1 code implementation • 17 May 2021 • Jörg Stork, Martin Zaefferer, Nils Eisler, Patrick Tichelmann, Thomas Bartz-Beielstein, A. E. Eiben
In addition to their undisputed success in solving classical optimization problems, neuroevolutionary and population-based algorithms have become an alternative to standard reinforcement learning methods.
1 code implementation • 16 May 2021 • Thomas Bartz-Beielstein, Marcel Dröscher, Alpar Gür, Alexander Hinterleitner, Olaf Mersmann, Dessislava Peeva, Lennard Reese, Nicolas Rehbach, Frederik Rehbach, Amrita Sen, Aleksandr Subbotin, Martin Zaefferer
Reasonable default values of these parameters were obtained in detailed discussions with medical professionals.
no code implementations • 3 Sep 2020 • Tom Peetz, Sebastian Vogt, Martin Zaefferer, Thomas Bartz-Beielstein
Generative Adversarial Networks (GANs) are powerful tools for generating new data for a variety of tasks.
2 code implementations • 14 Aug 2020 • Martin Zaefferer, Frederik Rehbach
However, predictions from data-driven models tend to be smoother than the ground-truth from which the training data is derived.
1 code implementation • 9 Jan 2020 • Frederik Rehbach, Martin Zaefferer, Boris Naujoks, Thomas Bartz-Beielstein
Few results from the literature show evidence, that under certain conditions, expected improvement may perform worse than something as simple as the predicted value of the surrogate model.
no code implementations • 22 Jul 2019 • Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein, A. E. Eiben
In detail, we investigate a) the potential of SMB-NE with respect to evaluation efficiency and b) how to select adequate input sets for the phenotypic distance measure in a reinforcement learning problem.
no code implementations • 16 Jul 2019 • Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier
This difference, the phenotypic distance, can then be used to situate these networks into a common input space, allowing us to produce surrogate models which can predict the performance of neural networks regardless of topology.
no code implementations • 9 Feb 2019 • Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein
For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency.
no code implementations • 20 Jul 2018 • Jörg Stork, Martin Zaefferer, Thomas Bartz-Beielstein
The topology optimization of artificial neural networks can be particularly difficult if the fitness evaluations require expensive experiments or simulations.
no code implementations • 10 Jul 2018 • Martin Zaefferer, Thomas Bartz-Beielstein, Günter Rudolph
We provide a proof-of-concept with 16 different distance measures for permutations.
no code implementations • 3 Jul 2018 • Martin Zaefferer, Jörg Stork, Oliver Flasch, Thomas Bartz-Beielstein
We investigate how different genotypic and phenotypic distance measures can be used to learn Kriging models as surrogates.
no code implementations • 3 Jul 2018 • Martin Zaefferer, Daniel Horn
Many real-world optimization problems require significant resources for objective function evaluations.
1 code implementation • 12 Dec 2017 • Thomas Bartz-Beielstein, Martin Zaefferer, Frederik Rehbach
The sequential parameter optimization (SPOT) package for R is a toolbox for tuning and understanding simulation and optimization algorithms.