Streamlining the development of data-driven industrial applications by automated machine learning

Kißkalt D, Mayr A, Lutz B, Rögele A, Franke J (2020)

Publication Type: Conference contribution

Publication year: 2020

Journal

Publisher: Elsevier B.V.

Book Volume: 93

Pages Range: 401-406

Conference Proceedings Title: Procedia CIRP

Event location: Chicago, IL

DOI: 10.1016/j.procir.2020.04.009

Abstract

Machine learning has often proven superior to traditional white-box modeling in industrial application scenarios. Yet the determinism in finding a solution close to the theoretical optimum is low due to human factors in the development process. Automated machine learning (AutoML), on the other hand, allows a complete automation of the machine learning pipeline from feature extraction and preprocessing to model selection and hyperparameter optimization. Using a popular open dataset, this paper exemplifies how AutoML can streamline the development of data-driven industrial applications. As a benchmark, results from existing approaches on the same dataset are used.

Authors with CRIS profile

How to cite

APA:

Kißkalt, D., Mayr, A., Lutz, B., Rögele, A., & Franke, J. (2020). Streamlining the development of data-driven industrial applications by automated machine learning. In Robert X. Gao, Kornel Ehmann (Eds.), Procedia CIRP (pp. 401-406). Chicago, IL, US: Elsevier B.V..

MLA:

Kißkalt, Dominik, et al. "Streamlining the development of data-driven industrial applications by automated machine learning." Proceedings of the 53rd CIRP Conference on Manufacturing Systems, CMS 2020, Chicago, IL Ed. Robert X. Gao, Kornel Ehmann, Elsevier B.V., 2020. 401-406.

BibTeX: Download