mlsanityData to 14 Oct 2026

On Interpretability of Artificial Neural Networks: A Survey

arXiv 2001.02522 ↗First posted 8 Jan 2020cs.LG cs.AI stat.MLcited by 88

Not on the map. Why?

Abstract (arXiv)

Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success in many important areas that deal with text, images, videos, graphs, and so on. However, the black-box nature of DNNs has become one of the primary obstacles for their wide acceptance in mission-critical applications such as medical diagnosis and therapy. Due to the huge potential of deep learning, interpreting neural networks has recently attracted much research attention. In this paper, based on our comprehensive taxonomy, we systematically review recent studies in understanding the mechanism of neural networks, describe applications of interpretability especially in medicine, and discuss future directions of interpretability research, such as in relation to fuzzy logic and brain science.

Key facts. Cited by 88 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 19; 2024: 19; 2025: 16; 2026: 6.

88 papers.

Sort:

By area:

  1. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  2. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  3. 2024Wav-KAN: Wavelet Kolmogorov-Arnold Networkscited by 122
  4. 2024Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Surveycited by 52
  5. 2022CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoisingcited by 46
  6. 2024Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Directioncited by 46
  7. 2023Gradient-based Parameter Selection for Efficient Fine-Tuningcited by 40
  8. 2024The Probabilities Also Matter: A More Faithful Metric for Faithfulness of Free-Text Explanations in Large Language Modelscited by 29
  9. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  10. 2023Understanding and Controlling a Maze-Solving Policy Networkcited by 22
  11. 2021Interpretable deep-learning models to help achieve the Sustainable Development Goalscited by 18
  12. 2023Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinesecited by 18
38 more
  1. 2024Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoderscited by 18
  2. 2024CausalFormer: An Interpretable Transformer for Temporal Causal Discoverycited by 17
  3. 2025From superposition to sparse codes: interpretable representations in neural networkscited by 16
  4. 2021On Recurrent Neural Networks for learning-based control: recent results and ideas for future developmentscited by 14
  5. 2024Endowing Interpretability for Neural Cognitive Diagnosis by Efficient Kolmogorov-Arnold Networkscited by 13
  6. 2023Interpretability of Machine Learning: Recent Advances and Future Prospectscited by 12
  7. 2023Unsupervised Deep Learning for IoT Time Seriescited by 11
  8. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  9. 2025Explainability in Practice: A Survey of Explainable NLP Across Various Domainscited by 11
  10. 2023Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressionscited by 10
  11. 2024Instruct Large Language Models to Generate Scientific Literature Survey Step by Stepcited by 10
  12. 2022Privacy Meets Explainability: A Comprehensive Impact Benchmarkcited by 9
  13. 2021Detecting Gender Bias in Transformer-based Models: A Case Study on BERTcited by 8
  14. 2023ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmapscited by 8
  15. 2021Damage detection using in-domain and cross-domain transfer learningcited by 7
  16. 2022A Survey of Neural Treescited by 7
  17. 2022Interpretability with full complexity by constraining feature informationcited by 7
  18. 2023Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videoscited by 7
  19. 2022Continuous-time identification of dynamic state-space models by deep subspace encodingcited by 6
  20. 2023Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networkscited by 6
  21. 2021Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderingscited by 5
  22. 2022Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Frameworkcited by 5
  23. 2023Spatial-Temporal Data Mining for Ocean Science: Data, Methodologies, and Opportunitiescited by 5
  24. 2025Tensorization is a powerful but underexplored tool for compression and interpretability of neural networkscited by 4
  25. 2025Optimistic critics can empower small actorscited by 4
  26. 2022TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosiscited by 3
  27. 2023On the Relationship Between Interpretability and Explainability in Machine Learningcited by 3
  28. 2023Rethinking Robustness of Model Attributionscited by 3
  29. 2025Neuro-Argumentative Learning with Case-Based Reasoningcited by 3
  30. 2025Uncertainty Estimation by Human Perception versus Neural Modelscited by 3
  31. 2025Leveraging Asynchronous Cross-border Market Data for Improved Day-Ahead Electricity Price Forecasting in European Marketscited by 3
  32. 2021Towards Understanding the Effectiveness of Attention Mechanismcited by 2
  33. 2021Creating Powerful and Interpretable Models with Regression Networkscited by 2
  34. 2022Manifoldron: Direct Space Partition via Manifold Discoverycited by 2
  35. 2022Automatic Infectious Disease Classification Analysis with Concept Discoverycited by 2
  36. 2023From Compass and Ruler to Convolution and Nonlinearity: On the Surprising Difficulty of Understanding a Simple CNN Solving a Simple Geometric Estimation Taskcited by 2
  37. 2023Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approachcited by 2
  38. 2024Clinical information extraction for Low-resource languages with Few-shot learning using Pre-trained language models and Promptingcited by 2

50 most cited of 88 All 88 (JSON)