Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning InterpretationDownload PDFOpen Website

2019 (modified: 11 Nov 2022)ICML 2019Readers: Everyone
Abstract: Current saliency map interpretations for neural networks generally rely on two key assumptions. First, they use first-order approximations of the loss function, neglecting higher-order terms such a...
0 Replies

Loading