Cargando…
Decoding Physics Information in DNNs
<!--HTML-->A more dedicated study on the information flow in DNNs will help us understand their behaviour and the deep connection between DNN models and the corresponding tasks. Taking into account our well-established physics analysis framework (observable-based), we present a novel way to in...
Autor principal: | Cheng, Taoli |
---|---|
Lenguaje: | eng |
Publicado: |
2019
|
Materias: | |
Acceso en línea: | http://cds.cern.ch/record/2672017 |
Ejemplares similares
-
The information theory of Deep Learning
por: Tishby, Naftali
Publicado: (2019) -
CMS Policies and Practises on providing information for reinterpretations
por: Ruiz, Jose
Publicado: (2021) -
Learning Invariant Representations using Mutual Information Regularization
por: Tan, Justin
Publicado: (2019) -
LHC measurements and additional information to use in global fits/EFT interpretations
por: Gilbert, Andrew
Publicado: (2021) -
Physics inspired Autonomous Feature Engineering
por: Rieger, Marcel
Publicado: (2019)