An Evolutionary Approach to Hyper-Parameter Optimization of Neural Networks

  • Marco StangEmail author
  • Christopher Meier
  • Vinzenz Rau
  • Eric Sax
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1018)


The last few years have increasingly been influenced by the emergence of neural networks for classification tasks. Due to the increasing size of the nets, especially concerning deep neural nets, the selection of the optimal topology becomes critical. A set of hyper-parameters determines the topology of a neural network. The selection of suitable hyper-parameters however, is time-consuming or requires expert knowledge. This paper examines the application of an evolutionary algorithm to optimize the hyper-parameters of a neural network. The result of the optimization by evolutionary algorithms can be applied for a variety of use-cases: i.e. detection of anomalies in CAN-bus data, object recognition for autonomous driving or the classification of hydraulic machinery oil.


Machine learning Hyper-parameter optimization Neural network Evolutionary algorithm 


  1. 1.
    Pfeffer, R., Ukas, P., Sax, E.: Potential of virtual test environments for the development of highly automated driving functions using neural networks. Presented at the (2019). Scholar
  2. 2.
    Weber, M., Pistorius, F., Sax, E., Maas, J., Zimmer, B.: A hybrid anomaly detection system for electronic control units featuring replicator neural networks. In: Arai, K., Kapoor, S., Bhatia, R. (eds.) Advances in Intelligent Systems and Computing, pp. 43–62. Springer, Cham (2019). Scholar
  3. 3.
    Weicker, K.: Anwendung evolutionärer Algorithmen. In: Evolutionäre Algorithmen, pp. 237–291. Springer (2015)Google Scholar
  4. 4.
    Kruse, R., et al.: Computational Intelligence: Eine methodische Einführung in Künstliche Neuronale Netze. Evol. Algorithmen, Fuzzy-Systeme und Bayes-Netze Vieweg + Teubner, Wiesbad (2011)Google Scholar
  5. 5.
    Nissen, V.: Evolutionäre Algorithmen: Darstellung, Beispiele, betriebswirtschaftliche Anwendungsmöglichkeiten, Wiesbaden 1994. Zugl.: Diss., Dt. Univ, (1994)Google Scholar
  6. 6.
    Gerdes, I., Klawonn, F., Kruse, R.: Evolutionäre Algorithmen: Genetische Algorithmen - Strategien und Optimierungsverfahren -Beispielanwendungen. Springer-Verlag (2013)Google Scholar
  7. 7.
    Pohlheim, H.: Evolutionäre Algorithmen: Verfahren. Springer-Verlag, Operatoren und Hinweise für die Praxis (2013)Google Scholar
  8. 8.

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Marco Stang
    • 1
    Email author
  • Christopher Meier
    • 1
  • Vinzenz Rau
    • 1
  • Eric Sax
    • 1
  1. 1.Institut für Technik der Informationsverarbeitung (ITIV)KarlsruheGermany

Personalised recommendations