Cargando…
Identifying the relevant dependencies of the neural network response on characteristics of the input space
The relation between the input and output spaces of neural networks (NNs) is investigated to identify those characteristics of the input space that have a large influence on the output for a given task. For this purpose, the NN function is decomposed into a Taylor expansion in each element of the in...
Autores principales: | Wunsch, Stefan, Friese, Raphael, Wolf, Roger, Quast, Günter |
---|---|
Lenguaje: | eng |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | https://dx.doi.org/10.1007/s41781-018-0012-1 http://cds.cern.ch/record/2639255 |
Ejemplares similares
-
Reducing the dependence of the neural network function to systematic uncertainties in the input space
por: Wunsch, Stefan, et al.
Publicado: (2019) -
Exploiting Apache Spark platform for CMS computing analytics
por: Meoni, Marco, et al.
Publicado: (2017) -
Review of High-Quality Random Number Generators
por: James, Frederick, et al.
Publicado: (2019) -
HEP Software Foundation Community White Paper Working Group -- Data Organization, Management and Access (DOMA)
por: Berzano, Dario, et al.
Publicado: (2018) -
HEP Software Foundation Community White Paper Working Group - Data and Software Preservation to Enable Reuse
por: Hildreth, M.D., et al.
Publicado: (2018)