no code implementations • 20 Jun 2018 • Justus T. C. Schwabedal, John C. Snyder, Ayse Cakmak, Shamim Nemati, Gari. D. Clifford
To quantify how well the distributions of the surrogates and the original data match, we evaluated a trained classifier on surrogates of correctly classified examples, and summarized these conditional predictions in a confusion matrix.