PatternNet and PatternLRP - Improving the interpretability of neural networks

By Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber, K. Müller, Sven Dähne. 2017

65 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Methods for interpreting and understanding deep neural networks (2017, background): “the input domain but also the statistics of the data within that domain were recently proposed [30].”
The (Un)reliability of saliency methods (2017, methodology): “2 raw gradients, PatternNet (PN), (Kindermans et al., 2017) and GuidedBackprop (GB) (Springenberg et al., 2015) produce identical saliency heatmaps for both networks.”
How do Humans Understand Explanations from Machine Learning Systems? An Evaluation of the Human-Interpretability of Explanation (2018, methodology): “…al., 2017], techniques for extracting local explanations from black-box models [Ribeiro et al., 2016, Lei et al., 2016, Adler et al., 2016, Selvaraju et al., 2016, Smilkov et al., 2017, Shrikumar et al., 2016, Kindermans et al., 2017, Ross et al., 2017], and visualization [Wattenberg et al., 2016].”
A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations (2018, background): “More recently, DeepLift (Shrikumar et al., 2017) and PatternNet (Kinder-mans et al., 2017) have been proposed to further improve the visual quality of backpropagation-based methods.”
Evaluating Feature Importance Estimates (2018, methodology): “…et al., 2017; Selvaraju et al., 2017; Sundararajan et al., 2017; Simonyan & Zisserman, 2015; Zeiler & Fergus, 2014; Springenberg et al., 2015; Kindermans et al., 2017; Montavon et al., 2017; Fong & Vedaldi, 2017; Dabkowski & Gal, 2017; Zhang et al., 2016; Shrikumar et al., 2017; Zhou et al.,…”
How Sensitive are Sensitivity-Based Explanations? (2019, background): “[10] proposes to calculate the signal of the image by removing distractors.”
Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents (2019, background): “[18] show that saliency methods do not produce analytically correct explanations for linear models and further reliability issues are discussed in [2, 13, 17].”
Improving the Interpretability of Neural Sentiment Classifiers via Data Augmentation (2019, methodology): “In general, a prediction explanation can be generated by using any local explanation method (Ribeiro et al., 2016; Kindermans et al., 2017; Fong and Vedaldi, 2017; Dabkowski and Gal, 2017).”
Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization (2020, result): “The PatterNet and PaternAttribution (Kindermans et al. 2017) methods yield similar results to LRP.”
Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers (2018, unknown): “However, recent work has shown that some of these methods fail to provide correct results and argue that we should develop explanation methods that work on simple models before scaling them up [90].”
On the (In)fidelity and Sensitivity for Explanations. (2019, background): “[14] propose to calculate the signal in the image by removing distractors.”
Accountability of AI Under the Law: The Role of Explanation (2017, unknown): “…an explanation of the system’s behavior overall, is known as local explanation [Ribeiro et al., 2016, Lei et al., 2016, Adler et al., 2016, Fong and Vedaldi, 2017, Selvaraju et al., 2016, Smilkov et al., 2017, Shrikumar et al., 2016, Kindermans et al., 2017, Ross et al., 2017, Singh et al., 2016].”