A systematic study reveals that gradient-based adversarial attacks can significantly distort explainable AI feature rankings ...
Quantization is an effective approach to accelerate deep neural networks by restricting their weights and activation functions to low precisions. However, the training objective (loss function) ...
Your institution does not have access to this book on JSTOR. Try searching on JSTOR for other items related to this book. Gradient-Based Methods for Deterministic Continuous Optimization Chapter One ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results