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

Source: [Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis](<https://www.sota2.com/research/paper/68fa6d801e209131cea3a20b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-18T05:00:11.457Z

Authors: Johannes Hirth, Tom Hanika

Published: 2022-09-27T16:38:24.000Z

## Abstract

We introduce \\emph{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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2209.13517>)

[PDF](<https://arxiv.org/pdf/2209.13517.pdf>)