You are here: Research Additional projects and publications Veröffentlichungen, die keinem Projekt und keiner Abteilung zugeordnet sind Publikationen Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations
  • Forschung - einfache Suche
  • Projektsuche
  • Publikationssuche

Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations

  • Autor/in: Schramowski, P., W. Stammer, S. Teso, A. Brugger, H.-G. Luigs, A.-Ka. Mahlein, K. Kersting
  • Jahr: 2020
  • Seite/n: 1-22, https://arxiv.org/pdf/2001.05371.pdf
Published in Projekt Veröffentlichungen, die keinem Projekt und keiner Abteilung zugeordnet sind / Abteilung Additional projects and publications

Abstract

Deep neural networks have shown excellent performances in many real-world applications such as plant phenotyping. Unfortunately, they may show “Clever Hans”-like behaviour— making use of confounding factors within datasets—to achieve high prediction rates. Rather than discarding the trained models or the dataset, we show that interactions between the learning system and the human user can correct the model. Specifically, we revise the models decision process by adding annotated masks during the learning loop and penalize decisions made for wrong reasons. In this way the decision strategies of the machine can be improved, focusing on relevant features, without considerably dropping predictive performance.
FaLang translation system by Faboba
IfZ - Institut für Zuckerrübenforschung · Holtenser Landstr. 77 · 37079 Göttingen · mail@ifz-goettingen.de · Impressum · Datenschutz previous_page
Suche läuft...

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.

Ok Decline
More information