
Publica
Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten. Unmasking Clever Hans predictors and assessing what machines really learn
| Nature Communications 10 (2019), Art. 1096, 8 S. ISSN: 2041-1723 |
| Bundesministerium für Bildung und Forschung BMBF (Deutschland) 01IS14013A |
|
| Englisch |
| Zeitschriftenaufsatz, Elektronische Publikation |
| Fraunhofer HHI () |
Abstract
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly intelligent behavior. Here we apply recent techniques for explaining decisions of state-of-the-art learning machines and analyze various tasks from computer vision and arcade games. This showcases a spectrum of problem-solving behaviors ranging from naive and short-sighted, to well-informed and strategic. We observe that standard performance evaluation metrics can be oblivious to distinguishing these diverse problem solving behaviors. Furthermore, we propose our semi-automated Spectral Relevance Analysis that provides a practically effective way of characterizing and validating the behavior of nonlinear learning machines. This helps to assess whether a learned model indeed delivers reliably for the problem that it was conceived for. Furthermore, our work intends to add a voice of caution to the ongoing excitement about machine intelligence and pledges to evaluate and judge some of these recent successes in a more nuanced manner.