On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation (original) (raw)
Fig 11
Taylor-approximated pixel-wise predictions for a multilayer neural network trained and tested on the MNIST data set.
Each group of four horizontally aligned panels shows—from left to right—the input digit, the Taylor root point _x_0, the gradient of the prediction function f at _x_0 of a specific digit class indicated by the subscript next to f and the approximated pixel-wise contributions for x.