Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers

Abstract

Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e.g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image. While this approach can be applied directly to generalized linear mappings, product type non-linearities are not covered. This paper proposes an approach to extend layer-wise relevance propagation to neural networks with local renormalization layers, which is a very common product-type non-linearity in convolutional neural networks. We evaluate the proposed method for local renormalization layers on the CIFAR-10, Imagenet and MIT Places datasets.

References in corpus (1)

• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition

Cited by in corpus (9)

• Axiomatic Attribution for Deep Networks
• Methods for Interpreting and Understanding Deep Neural Networks
• How Important Is a Neuron?
• Towards falsifiable interpretability research
• Self-Attention Attribution: Interpreting Information Interactions Inside Transformer
• Global Explanations of Neural Networks: Mapping the Landscape of Predictions
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• A Note about: Local Explanation Methods for Deep Neural Networks lack Sensitivity to Parameter Values
• Attribution in Scale and Space