Variant Approach for Identifying Spurious Relations That Deep Learning Models Learn

Variant Approach for Identifying Spurious Relations That Deep Learning Models Learn

A deep learning (DL) model learns a function relating a set of input variables with a set of target variables. While the representation of this function in form of the DL model often lacks interpretability, several interpretation methods exist that provide descriptions of the function (e.g., measure...

Full description

Bibliographic Details
Main Authors: Tobias Tesch, Stefan Kollet, Jochen Garcke
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-09-01
Series:Frontiers in Water
Subjects:
interpretable deep learning
statistical model
machine learning
spurious correlation
causality
hydrometeorology
Online Access:https://www.frontiersin.org/articles/10.3389/frwa.2021.745563/full

Internet

https://www.frontiersin.org/articles/10.3389/frwa.2021.745563/full

Similar Items