KIT | KIT-Bibliothek | Impressum | Datenschutz

A Step towards Explainable Artificial Neural Networks in Image Processing by Dataset Assessment

Heide, Nina Felicitas; Albrecht, Alexander; Heizmann, Michael


Artificial neural networks, image processing, premodeling explainability, robot vision systems

Abstract (englisch):

We propose a methodology for generalized exploratory data analysis focusing on artificial neural network (ANN) methods. Our method is denoted IC-ACC due to the combined assessment of information content (IC) and accuracy (ACC) and aims at answering a frequently posed question in ANN research: ”What is good data?” As the dataset has the primary influence on the development of the model, IC-ACC provides a step towards explainable ANN methods in the pre-modeling stage by a better insight in the dataset. With this insight, detrimental data can be eliminated before a negative influence on the ANN performance occurs. ... mehr

Verlagsausgabe §
DOI: 10.5445/IR/1000129209
Veröffentlicht am 01.02.2021
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Proceedingsbeitrag
Publikationsmonat/-jahr 11.2020
Sprache Englisch
Identifikator ISBN: 978-3-7315-1053-6
KITopen-ID: 1000129209
Erschienen in Forum Bildverarbeitung 2020. Ed.: T. Längle ; M. Heizmann
Verlag KIT Scientific Publishing
Seiten 291-303
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page