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

arXiv: https://arxiv.org/abs/2209.13517 · HTML: https://mlsanity.com/paper/2209.13517/

## Key facts

- Cited by 1 papers 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 (most cited first, 13 of 13)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent](https://mlsanity.com/paper/1902.06720/) (2019)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networks](https://mlsanity.com/paper/1801.03454/) (2018)
- [Neural Kernels Without Tangents](https://mlsanity.com/paper/2003.02237/) (2020)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Fruit recognition from images using deep learning](https://mlsanity.com/paper/1712.00580/) (2017)
- [On the Lattice of Conceptual Measurements](https://mlsanity.com/paper/2012.05267/) (2020)
- [Quantifying the Conceptual Error in Dimensionality Reduction](https://mlsanity.com/paper/2106.06815/) (2021)

## Built on by (most cited first, 1 of 1)

- [Scaling Dimension](https://mlsanity.com/paper/2302.09101/) (2023)

## 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.