Get the Insights of your Neural Network

Interpretability methods to analyze the behavior and individual predictions of modern neural networks. Implemented methods are: 'Connection Weights' described by Olden et al. (2004) , Layer-wise Relevance Propagation ('LRP') described by Bach et al. (2015) , Deep Learning Important Features ('DeepLIFT') described by Shrikumar et al. (2017) and gradient-based methods like 'SmoothGrad' described by Smilkov et al. (2017) , 'Gradient x Input' described by Baehrens et al. (2009) or 'Vanilla Gradient'.