Cargando…
Identifying the relevant dependencies of the neural network response on characteristics of the input space
<!--HTML-->The use of neural networks in physics analyses poses new challenges for the estimation of systematic uncertainties. Since the key to a proper estimation of uncertainties is the precise understanding of the algorithm, novel methods for the detailed study of the trained neural network...
Autor principal: | Wunsch, Stefan |
---|---|
Lenguaje: | eng |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2312450 |
Ejemplares similares
-
Identification of Hadronically Decaying W Bosons and Top Quarks Using High-Level Features as Input to Boosted Decision Trees and Deep Neural Networks in ATLAS at 13 TeV
por: Akilli, Ece
Publicado: (2017) -
Identifying the relevant dependencies of the neural network response on characteristics of the input space
por: Wunsch, Stefan, et al.
Publicado: (2018) -
Tutorial: Keras/TensorFlow
por: Wunsch, Stefan
Publicado: (2018) -
Tutorial 3: Keras and TMVA interfaces
por: Wunsch, Stefan
Publicado: (2017) -
Interpreting Deep Neural Networks and their Predictions
por: Samek, Wojciech
Publicado: (2018)