Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Can AutoML outperform humans?

An evaluation on popular OpenML datasets using AutoML Benchmark
 
: Hanussek, Marc; Blohm, Matthias; Kintz, Maximilien

:
Volltext (PDF; )

Karam, Omar H. (Conference Chair) ; Association for Computing Machinery -ACM-:
AIRC 2020, 2nd International Conference on Artificial Intelligence, Robotics and Control : December 26th-28th 2020, Online
New York: ACM, 2020
ISBN: 978-1-4503-8926-6
S.29-32
International Conference on Artificial Intelligence, Robotics and Control (AIRC) <2, 2020, Online>
Englisch
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IAO ()

Abstract
In the last few years, Automated Machine Learning (AutoML) has gained much attention. With that said, the question arises whether AutoML can outperform results achieved by human data scientists. This paper compares four AutoML frameworks on 12 different popular datasets from OpenML; six of them supervised classification tasks and the other six supervised regression ones. Additionally, we consider a real-life dataset from one of our recent projects. The results show that the automated frameworks perform better or equal than the machine learning community in 7 out of 12 OpenML tasks.

: http://publica.fraunhofer.de/dokumente/N-634589.html