KIT | KIT-Bibliothek | Impressum | Datenschutz

Reducing the Dependence of the Neural Network Function to Systematic Uncertainties in the Input Space

Wunsch, Stefan; Jörger, Simon; Wolf, Roger; Quast, Günter

Abstract:
Applications of neural networks to data analyses in natural sciences are complicated by the fact that many inputs are subject to systematic uncertainties. To control the dependence of the neural network function to variations of the input space within these systematic uncertainties, several methods have been proposed. In this work, we propose a new approach of training the neural network by introducing penalties on the variation of the neural network output directly in the loss function. This is achieved at the cost of only a small number of additional hyperparameters. It can also be pursued by treating all systematic variations in the form of statistical weights. The proposed method is demonstrated with a simple example, based on pseudo-experiments, and by a more complex example from high-energy particle physics.

Open Access Logo


Verlagsausgabe §
DOI: 10.5445/IR/1000123325
Veröffentlicht am 04.09.2020
Originalveröffentlichung
DOI: 10.1007/s41781-020-00037-9
Dimensions
Zitationen: 9
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Experimentelle Teilchenphysik (ETP)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 12.2020
Sprache Englisch
Identifikator ISSN: 2510-2036, 2510-2044
KITopen-ID: 1000123325
Erschienen in Computing and software for big science
Verlag Springer
Band 4
Heft 1
Seiten Article: 5
Vorab online veröffentlicht am 23.02.2020
Nachgewiesen in Dimensions
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page