mlsanityData to 7 Oct 2026

Interpreting Neural Network Judgments via Minimal, Stable, and Symbolic Corrections

arXiv 1802.07384 ↗First posted 21 Feb 2018cs.LG cs.AI stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

We present a new algorithm to generate minimal, stable, and symbolic corrections to an input that will cause a neural network with ReLU activations to change its output. We argue that such a correction is a useful way to provide feedback to a user when the network's output is different from a desired output. Our algorithm generates such a correction by solving a series of linear constraint satisfaction problems. The technique is evaluated on three neural network models: one predicting whether an applicant will pay a mortgage, one predicting whether a first-order theorem can be proved efficiently by a solver using certain heuristics, and the final one judging whether a drawing is an accurate rendition of a canonical drawing of a cat.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 5; 2023: 4; 2024: 3.

19 papers.

Sort:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  3. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  4. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  5. 2021Fair Normalizing Flowscited by 38
  6. 2022On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbationscited by 32
  7. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  8. 2023Provably Bounding Neural Network Preimagescited by 28
  9. 2023Towards Trustworthy Explanation: On Causal Rationalizationcited by 19
  10. 2023XAIR: A Framework of Explainable AI in Augmented Realitycited by 17
  11. 2024Neuro-Symbolic AI: Explainability, Challenges, and Future Trendscited by 10
  12. 2021Interpretable Machine Learning: Moving From Mythos to Diagnosticscited by 9
7 more
  1. 2022Cardinality-Minimal Explanations for Monotonic Neural Networkscited by 8
  2. 2024Provably Safe Neural Network Controllers via Differential Dynamic Logiccited by 7
  3. 2022ReX: A Framework for Incorporating Temporal Information in Model-Agnostic Local Explanation Techniquescited by 5
  4. 2024Sparse and Faithful Explanations Without Sparse Modelscited by 5
  5. 2021Synthesizing Pareto-Optimal Interpretations for Black-Box Modelscited by 3
  6. 2021Instructive artificial intelligence (AI) for human training, assistance, and explainabilitycited by 2
  7. 2023Symbolic Metamodels for Interpreting Black-boxes Using Primitive Functionscited by 2