Didactic approach to the development and optimisation of artificial neural networks

A practical project on autonomous driving

Authors

  • Ron van de Sand TH Wildau
  • Sebastian Schulz TH Wildau
  • Jörg Reiff-Stephan
  • Alexander Stolpmann TH Wildau

DOI:

https://doi.org/10.17560/atp.v61i9.2405

Abstract

The growing complexity of automation systems will require the increased use of machine learning methods, placing new demands on teaching at universities in the field of engineering. This article describes a didactic approach to project-based knowledge transfer using the example of autonomous driving. In the project, an artificial neural network (ANN) is developed for the control of an autonomous driving system. In addition, the functional principle of genetic algorithms is taught as a global optimization method and applied as a methodology for the structural optimization of ANNs.

References

Ge, Z., Song, Z., Ding, S. X., Huang, B. (2017). Data mining and analytics in the process industry: The role of machine learning. IEEE Access, 5, (pp. 20590-20616).

Statista GmbH. (2019). Prognose zum Umsatz mit Unternehmensanwendungen im Bereich künstliche Intelligenz in Europa von 2016 bis 2025. Abgerufen von: https://de.statista.com/statistik/daten/studie/620513/umfrage/umsatz-mit-anwendungen-im-bereich-kuenstliche-intelligenz-in-europa/ 2019

Sapp, C. E. (2017). Preparing and architecting for machine learning. Gartner Technical Professional Advice, (pp. 1-37).

Heidling, E., Meil, P., Neumer, J. (2019). Ingenieurinnen und Ingenieure für Industrie 4.0. In IMPULS-Stiftung für den Maschinenbau, den Anlagenbau und die Informationstechnik, (pp. 15), Berlin, 2019.

Janglová, D. (2004). Neural networks in mobile robot motion. International Journal of Advanced Robotic Systems, 1(1), (pp. 2).

Goodfellow, I., Bengio, Y., Courville, A. (2016). Deep learning. MIT press.

Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1988). Learning representations by back-propagating errors. Cognitive modeling, 5(3), (pp. 1).

Itano, F., de Sousa, M. A. D. A., Del-Moral-Hernandez, E. (2018). Extending MLP ANN hyper-parameters Optimization by using Genetic Algorithm. In 2018 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.

Mitchell, M. (1999). An Introduction to Genetic Algorithm. Cambridge (MA), London: MIT Press.

Stolpmann, A., Dooley, L. (2000). A Texture Classification System Using Statistical and Soft-Computing Methods. In Texture Analysis in Machine Vision, Series in Machine Perception and Artificial Intelligence, World Scientific (pp. 53-65), Singapur, 2000.

Downloads

Published

2019-09-26

Issue

Section

Article / Peer Review