no code implementations • 18 Sep 2022 • Minh N. Vu, Truc D. Nguyen, My T. Thai
In this work, we propose NeuCEPT, a method to locally discover critical neurons that play a major role in the model's predictions and identify model's mechanisms in generating those predictions.
no code implementations • 5 Jun 2019 • Minh N. Vu, Truc D. Nguyen, NhatHai Phan, Ralucca Gera, My T. Thai
Given a classifier's prediction and the corresponding explanation on that prediction, c-Eval is the minimum-distortion perturbation that successfully alters the prediction while keeping the explanation's features unchanged.