Browsing NR vitenarkiv by Author "Glad, Ingrid Kristine"
Now showing items 1-5 of 5
-
A comparative study of methods for estimating model-agnostic Shapley value explanations
Olsen, Lars Henry Berge; Glad, Ingrid Kristine; Jullum, Martin; Aas, Kjersti (Journal article; Peer reviewed, 2024)Shapley values originated in cooperative game theory but are extensively used today as a model-agnostic explanation framework to explain predictions made by complex machine learning models in the industry and academia. ... -
Estimating the effect of biofouling on ship shaft power based on sensor measurements
Bakka, Haakon Christopher; Rognebakke, Hanne Therese Wist; Glad, Ingrid Kristine; Haff, Ingrid Hobæk; Vanem, Erik (Journal article; Peer reviewed, 2022) -
Partially linear monotone methods with automatic variable selection and monotonicity direction discovery
Engebretsen, Solveig; Glad, Ingrid Kristine (Journal article; Peer reviewed, 2020) -
Scalable change and anomaly detection in cross-correlated data
Tveten, Martin; Glad, Ingrid Kristine; Hjort, Nils Lid (Doctoral thesis, 2021) -
Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features
Olsen, Lars Henry Berge; Glad, Ingrid Kristine; Jullum, Martin; Aas, Kjersti (Journal article; Peer reviewed, 2022)Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoretical properties and a sound mathematical ...