Explainable Artificial Intelligence: Analyse und Visualisierung des Lernprozesses eines Convolutional Neural Network zur Erkennung deutscher Straßenverkehrsschilder (Explainable Artificial Intelligence: Analysis and Visualization of a Convolutional Neural Network for the Recognition of German Traffic Signs)

Schriftenreihe des Instituts für Empirie & Statistik der FOM Hochschule 2021 Band 26

114 Pages Posted: 22 Jul 2021

See all articles by Robin Maasjosthusmann

Robin Maasjosthusmann

FOM University of Applied Sciences for Economics and Management

Frank Lehrbass

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting); FOM University of Applied Sciences for Economics and Management; University of the Bundesbank

Date Written: June 29, 2021

Abstract

German abstract: Diese Studie untersucht, welche Merkmale der Schilder ein CNN zur Klassifizierung von deutschen Straßenverkehrsschildern verwendet und wie anfällig der Prozess der Wiedererkennung für äußere Einflüsse ist.

English abstract: This study investigates which features of German Traffic Signs are used by a CNN for classification. In addition it is explored how error-prone this technique is if the signs are manipulated.

Note: Downloadable document available in German.

Keywords: Autonomous driving, self-driving car, autonomous vehicle, control systems

JEL Classification: L62, L63

Suggested Citation

Maasjosthusmann, Robin and Lehrbass, Frank and Lehrbass, Frank, Explainable Artificial Intelligence: Analyse und Visualisierung des Lernprozesses eines Convolutional Neural Network zur Erkennung deutscher Straßenverkehrsschilder (Explainable Artificial Intelligence: Analysis and Visualization of a Convolutional Neural Network for the Recognition of German Traffic Signs) (June 29, 2021). Schriftenreihe des Instituts für Empirie & Statistik der FOM Hochschule 2021 Band 26, Available at SSRN: https://ssrn.com/abstract=3876442

Robin Maasjosthusmann

FOM University of Applied Sciences for Economics and Management ( email )

Toulouser Allee 53
Dusseldorf, 40476
Germany

Frank Lehrbass (Contact Author)

FOM University of Applied Sciences for Economics and Management ( email )

Toulouser Allee 53
Dusseldorf, 40476
Germany

L*PARC (Lehrbass Predicitive Analytics and Risk Consulting) ( email )

Dusseldorf
Germany

HOME PAGE: http://lehrbass.de

University of the Bundesbank ( email )

Schloss
Hachenburg, 57627
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
71
Abstract Views
370
Rank
536,354
PlumX Metrics