mlsanityData to 7 Oct 2026

Explaining Trained Neural Networks with Semantic Web Technologies: First Steps

arXiv 1710.04324 ↗First posted 11 Oct 2017cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the input-output behavior of trained artificial neural networks. We apply existing Semantic Web technologies in order to provide an experimental proof of concept.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 3; 2023: 4; 2024: 2.

13 papers.

Sort:

By area:

  1. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54
  2. 2021Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use casescited by 39
  3. 2021Learning Concept Lengths Accelerates Concept Learning in ALCcited by 10
  4. 2022Towards Human-Compatible XAI: Explaining Data Differentials with Concept Induction over Background Knowledgecited by 6
  5. 2024On the Value of Labeled Data and Symbolic Methods for Hidden Neuron Activation Analysiscited by 6
  6. 2021Combining Sub-Symbolic and Symbolic Methods for Explainabilitycited by 3
  7. 2022Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphscited by 2
  8. 2023Explaining Deep Learning Hidden Neuron Activations using Concept Inductioncited by 2
  9. 2023Understanding CNN Hidden Neuron Activations Using Structured Background Knowledge and Deductive Reasoningcited by 2
  10. 2023Requirements for Explainability and Acceptance of Artificial Intelligence in Collaborative Workcited by 1
  11. 2024Error-margin Analysis for Hidden Neuron Activation Labelscited by 1
  12. 2022A Dynamic Data Driven Approach for Explainable Scene Understandingcited by 0
1 more
  1. 2023What can knowledge graph alignment gain with Neuro-Symbolic learning approaches?cited by 0