Search Results for author:
Found 2 papers, 0 papers with code
Measuring Feature Dependency of Neural Networks by Collapsing Feature Dimensions in the Data Manifold
Our method is based on the principle that if a model is dependent on a feature, then removal of that feature should significantly harm its performance.
Feature Gradient Flow for Interpreting Deep Neural Networks in Head and Neck Cancer Prediction
This paper introduces feature gradient flow, a new technique for interpreting deep learning models in terms of features that are understandable to humans.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
