Tweeted By @ChristophMolnar
Explanation algorithms for neural network predictions are like yogurts in a supermarket. Choice overload.
— Christoph Molnar (@ChristophMolnar) May 17, 2019
LRP
LIME
Integrated Gradients
deconvnet
Occlusion
DeepShap
DeepLift
Deep Taylor Decomposition
Gradient* Input
Grad-CAM
Guided Backpropagation
Saliency Map
... pic.twitter.com/6GBbnuMxQM