Building and Interpreting Deep Similarity Models

Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on distances or similarities. Before similarities are used for training an actual machine learning model, we would like to verify that they are bound to meaningful patterns in the data. I...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2022-03, Vol.44 (3), p.1149-1161
Hauptverfasser:	Eberle, Oliver, Buttner, Jochen, Krautli, Florian, Muller, Klaus-Robert, Valleriani, Matteo, Montavon, Gregoire
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Anomalies Artificial neural networks Cluster Analysis Clustering Data models Deep learning deep neural networks digital humanities explainable machine learning Feature extraction Kernel functions layer-wise relevance propagation Machine Learning Neural networks Neural Networks, Computer Robustness Similarity Taylor series
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!