!!Thomas Bäck - Publications
\\
5 Publications from last five years (2022):\\
\\
A. Camero, H. Wang, E. Alba, T. Baeck: Bayesian neural architecture search using a training-free performance metric. Applied Soft Computing 106, 107356, 2021.\\
\\
A new approach for neural architecture search that uses a training-free performance metric, such that deep neural network architectures can be evalated much faster than before.\\
\\
C. Doerr, F. Ye, N. Horesh, H. Wang, O. Shir, T. Baeck: Benchmarking discrete optimization heuristics with IOHprofiler. Applied Soft Computing 88, 106027, 2020.\\
\\
This paper introduces a new framework for benchmarking optimization heuristics. This framework is widely adopted in the field now, due to its advanced capabilities for comparing search heuristics, visualizing the results, and running statistically sound evaluations and tests on the results. \\
\\
B. van Stein, H. Wang, W. Kowalczyk, M. Emmerich, T. Baeck: Cluster-based Kriging approximation algorithms for complexity reduction. Applied Intelligence, 50(3):778-791, 2020.\\
\\
A new method for reducing the computational complexity of Kriging-based metamodels is introduced in this paper. \\
\\
K. Yang, M.T.M. Emmerich, A. Deutz, T. Baeck: Multi-Objective Bayesian Global Optimization using Expected Hypervolume Improvement Gradient. Swarm and Evolutionary Computation, 44:945-956, Elsevier, Feb. 2019. \\
\\
This paper introduces a powerful extension of Bayesian global optimization into the multi-objective optimization domain. The approach uses the expected hypervolume gradient, which is also introduced in this paper.\\
\\
S. Bagheri, W. Konen, M. Emmerich, T. Baeck: Self-adjusting parameter control for surrogate-assisted constrained optimization under limited budgets. Applied Soft Computing 61:377-393, Elsevier, December 2017. \\
\\
Addressing real-world optimization problems with severely limited function evaluation budgets, this paper introduces a new algorithm for handling such problems and illustrates its favorable properties by means of real-world application examples.\\
\\
__Books/Handbooks:__\\
\\
T. Baeck, C. Foussette, P. Krause: Contemporary Evolution Strategies, Springer, Berlin, 2013. \\
\\
This book provides an overview of variants of evolution strategies and a concise introduction to this group of algorithms. Moreover, it investigates the case of small numbers of function evaluations, especially less than 1.000, as it is often the case for real-world problems.\\
\\
G. Rozenberg, Th. Baeck, J.N. Kok, editors. Handbook of Natural Computation. Springer, Berlin, 2013. \\
\\
The reference handbook for the field of Natural Computation.\\
\\
T. Baeck, D. B. Fogel, Z. Michalewicz, editors. Handbook of Evolutionary Computation. Oxford University Press, New York, and Institute of Physics Publishing, Bristol, 1997. \\
\\
The reference handbook for the field of Evolutionary Computation.\\
\\
T. Baeck: Evolutionary Algorithms in Theory and Practice, Oxford University Press, New York, 1996. \\
\\
This book provides the description of the unified framework of Evolutionary Computation, developed by Thomas Bäck. For the first time, it demonstrates how these algorithms fit one single formal concept, and how their components can beexchanged between them and adapted to work within each one of them. This approach opened up a new design space for evolutionary algorithms and meta-heuristics. \\
\\
H-Index: 62, with a total of 38,500 citations (Nov. 27, 2021).