Very concise toy example of integrated gradients (a method to reveal areas of attention of neural networks in input images)
Integrated Gradients were proposed by Sundararajan et al. in the paper:
Sundararajan, Mukund, Ankur Taly, and Qiqi Yan. "Axiomatic attribution for deep networks." In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 3319-3328. JMLR. org, 2017