Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 1 of 1
Full-Text Articles in Engineering
Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue
Gradient Free Sign Activation Zero One Loss Neural Networks For Adversarially Robust Classification, Yunzhe Xue
Dissertations
The zero-one loss function is less sensitive to outliers than convex surrogate losses such as hinge and cross-entropy. However, as a non-convex function, it has a large number of local minima, andits undifferentiable attribute makes it impossible to use backpropagation, a method widely used in training current state-of-the-art neural networks. When zero-one loss is applied to deep neural networks, the entire training process becomes challenging. On the other hand, a massive non-unique solution probably also brings different decision boundaries when optimizing zero-one loss, making it possible to fight against transferable adversarial examples, which is a common weakness in deep learning …