mlsanityData to 14 Oct 2026

How to Explain Neural Networks: an Approximation Perspective

arXiv 2105.07831 ↗First posted 17 May 2021cs.LG cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The lack of interpretability has hindered the large-scale adoption of AI technologies. However, the fundamental idea of interpretability, as well as how to put it into practice, remains unclear. We provide notions of interpretability based on approximation theory in this study. We first implement this approximation interpretation on a specific model (fully connected neural network) and then propose to use MLP as a universal interpreter to explain arbitrary black-box models. Extensive experiments demonstrate the effectiveness of our approach.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

40 of 55 references.

References · 40

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  8. 2013Visualizing and Understanding Convolutional Networkscited by 2,290
  9. 2020Knowledge Distillation: A Surveycited by 1,603
  10. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  11. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,109
28 more
  1. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  2. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
  3. 2016The Mythos of Model Interpretabilitycited by 721
  4. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 612
  5. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  6. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  7. 2015Understanding Neural Networks Through Deep Visualizationcited by 334
  8. 2017The (Un)reliability of saliency methodscited by 333
  9. 2016Top-down Neural Attention by Excitation Backpropcited by 321
  10. 2020A Survey on Neural Network Interpretabilitycited by 291
  11. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
  12. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
  13. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  14. 2019Full-Gradient Representation for Neural Network Visualizationcited by 191
  15. 2014Object Detectors Emerge in Deep Scene CNNscited by 179
  16. 2017Interpretable Convolutional Neural Networkscited by 162
  17. 2019Deep ReLU Networks Have Surprisingly Few Activation Patternscited by 161
  18. 2020On Interpretability of Artificial Neural Networks: A Surveycited by 88
  19. 2020Explainable Artificial Intelligence: a Systematic Reviewcited by 79
  20. 2018Geometric Understanding of Deep Learningcited by 41
  21. 2018Improving the Interpretability of Deep Neural Networks with Knowledge Distillationcited by 38
  22. 2020Empirical Studies on the Properties of Linear Regions in Deep Neural Networkscited by 36
  23. 2018Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solutioncited by 32
  24. 2019Characterizing the Decision Boundary of Deep Neural Networkscited by 32
  25. 2020Understanding the Decision Boundary of Deep Neural Networks: An Empirical Studycited by 20
  26. 2018On the Decision Boundary of Deep Neural Networkscited by 11
  27. 2020Explaining Predictions by Approximating the Local Decision Boundarycited by 7
  28. 2020Measuring Model Complexity of Neural Networks with Curve Activation Functionscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Any Deep ReLU Network is Shallowcited by 6