Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers

Add code
Oct 15, 2019
George Kesidis, David J. Miller
Figure 1 for Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers
Figure 2 for Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers
Figure 3 for Notes on Lipschitz Margin, Lipschitz Margin Training, and Lipschitz Margin p-Values for Deep Neural Network Classifiers

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We provide a local class purity theorem for Lipschitz continuous, half-rectified DNN classifiers. In addition, we discuss how to train to achieve classification margin about training samples. Finally, we describe how to compute margin p-values for test samples.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon