1. Deep inside convolutional networks: Visualising image classification models and saliency maps;Simonyan,2013
2. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation;Bach;PLOS ONE,2015
3. A. Shrikumar, P. Greenside, A. Kundaje, Learning Important Features Through Propagating Activation Differences, in: International Conference on Machine Learning, 2017, pp. 3145–3153.
4. A unified approach to interpreting model predictions;Lundberg,2017
5. “Why should I trust you?”: Explaining the predictions of any classifier;Ribeiro,2016