mlsanityData to 7 Oct 2026

Learning from learning machines: a new generation of AI technology to meet the needs of science

arXiv 2111.13786 ↗First posted 27 Nov 2021cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

We outline emerging opportunities and challenges to enhance the utility of AI for scientific discovery. The distinct goals of AI for industry versus the goals of AI for science create tension between identifying patterns in data versus discovering patterns in the world from data. If we address the fundamental challenges associated with "bridging the gap" between domain-driven scientific models and data-driven AI learning machines, then we expect that these AI models can transform hypothesis generation, scientific discovery, and the scientific process itself.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 36 of its 124 references that are in the map. First posted on arXiv 27 Nov 2021.

Builds on

36 of 124 references.

References · 36

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2018Sanity Checks for Saliency Mapscited by 1,149
  7. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  8. 2021Characterizing possible failure modes in physics-informed neural networkscited by 632
  9. 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 536
  10. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  11. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  12. 2020Discovering Symbolic Models from Deep Learning with Inductive Biasescited by 335
24 more
  1. 2017The (Un)reliability of saliency methodscited by 331
  2. 2019Interpretable machine learning: definitions, methods, and applicationscited by 303
  3. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  4. 2020Decoupling Representation Learning from Reinforcement Learningcited by 263
  5. 2018Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equationscited by 233
  6. 2018Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learningcited by 211
  7. 2020Predicting trends in the quality of state-of-the-art neural networks without access to training or testing datacited by 113
  8. 2020Explaining Explanations: Axiomatic Feature Interactions for Deep Networkscited by 103
  9. 2020AI Poincar'e: Machine Learning Conservation Laws from Trajectoriescited by 77
  10. 2020A Random Matrix Analysis of Random Fourier Features: Beyond the Gaussian Kernel, a Precise Phase Transition, and the Corresponding Double Descentcited by 69
  11. 2019Veridical Data Sciencecited by 65
  12. 2018Learning to Predict the Cosmological Structure Formationcited by 38
  13. 2016Neural Random Forestscited by 25
  14. 2019Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based roboticscited by 21
  15. 2021Post-mortem on a deep learning contest: a Simpson's paradox and the complementary roles of scale metrics versus shape metricscited by 19
  16. 2020Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classificationcited by 18
  17. 2019The Scientific Method in the Science of Machine Learningcited by 15
  18. 2014Think Locally, Act Locally: The Detection of Small, Medium-Sized, and Large Communities in Large Networkscited by 8
  19. 2017Interpreting Convolutional Neural Networks Through Compressioncited by 5
  20. 2019The scientific case for brain simulationscited by 3
  21. 2016Mapping the Similarities of Spectra: Global and Locally-biased Approaches to SDSS Galaxy Datacited by 2
  22. 2016Towards a theory of cortical columns: From spiking neurons to interacting neural populations of finite sizecited by 2
  23. 2017Union of Intersections (UoI) for Interpretable Data Driven Discovery and Predictioncited by 2
  24. 2020Machine learning with persistent homology and chemical word embeddings improves prediction accuracy and interpretability in metal-organic frameworkscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2024Rethinking Interpretability in the Era of Large Language Modelscited by 110
  2. 2022Learning continuous models for continuous physicscited by 28
  3. 2025Advancing the Scientific Method with Large Language Models: From Hypothesis to Discoverycited by 7