FACILITATING INTERPRETABILITY OF CLASSIFICATION MODEL

A system and computer-implemented method are provided for generating a visualization of the classification uncertainty of a classification model which is applied to clinical data, wherein said visualization is provided in a lower-dimensional space which is obtained by applying a non-linear and manif...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: PEZZOTTI, Nicola, KUSTRA, Jacek Lukasz
Format: Patent
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A system and computer-implemented method are provided for generating a visualization of the classification uncertainty of a classification model which is applied to clinical data, wherein said visualization is provided in a lower-dimensional space which is obtained by applying a non-linear and manifold preserving dimensionality reduction technique to feature vectors of the clinical data. The visualization techniques consider the classification model as a 'black box' by not being dependent on internal parameters of the classification model.