mlsanityData to 14 Oct 2026

Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis

arXiv 2209.13517 ↗First posted 27 Sep 2022cs.LG cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce conceptual views as a formal framework grounded in Formal Concept Analysis for globally explaining neural networks. Experiments on twenty-four ImageNet models and Fruits-360 show that these views faithfully represent the original models, enable architecture comparison via Gromov--Wasserstein distance, and support abductive learning of human-comprehensible rules from neurons.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 13 of its 28 references that are in the map. First posted on arXiv 27 Sep 2022.

Builds on

13 of 28 references.

References · 13

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2019Similarity of Neural Network Representations Revisitedcited by 1,755
  4. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  5. 2020Concept Bottleneck Modelscited by 1,032
  6. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 738
  7. 2022Post-hoc Concept Bottleneck Modelscited by 293
  8. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 129
  9. 2020Neural Kernels Without Tangentscited by 56
  10. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  11. 2017Fruit recognition from images using deep learningcited by 35
  12. 2020On the Lattice of Conceptual Measurementscited by 8
1 more
  1. 2021Quantifying the Conceptual Error in Dimensionality Reductioncited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Scaling Dimensioncited by 2