Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples

There is great interest in using formal methods to guarantee the reliability of deep neural networks. However, these techniques may also be used to implant carefully selected input-output pairs. We present initial results on a novel technique for using SMT solvers to fine tune the weights of a ReLU...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Papusha, Ivan, Wu, Rosa, Brulé, Joshua, Kouskoulas, Yanni, Genin, Daniel, Schmidt, Aurora
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Mathematics - Optimization and Control Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!