Adding Interpretability to Neural Knowledge DNA - Publication - MOST Wiedzy

Search

Adding Interpretability to Neural Knowledge DNA

Abstract

This paper proposes a novel approach that adds the interpretability to Neural Knowledge DNA (NK-DNA) via generating a decision tree. The NK-DNA is a promising knowledge representation approach for acquiring, storing, sharing, and reusing knowledge among machines and computing systems. We introduce the decision tree-based generative method for knowledge extraction and representation to make the NK-DNA more explainable. We examine our approach through an initial case study. The experiment results show that the proposed method can transform the implicit knowledge stored in the NK-DNA into explicitly represented decision trees bringing fair interpretability to neural network-based intelligent systems.

Citations

  • 0

    CrossRef

  • 0

    Web of Science

  • 0

    Scopus

Authors (4)

Cite as

Full text

full text is not available in portal

Keywords

Details

Category:
Articles
Type:
artykuły w czasopismach
Published in:
CYBERNETICS AND SYSTEMS no. 53, pages 500 - 509,
ISSN: 0196-9722
Language:
English
Publication year:
2022
Bibliographic description:
Xiao J., Liu T., Zhang H., Szczerbicki E.: Adding Interpretability to Neural Knowledge DNA// CYBERNETICS AND SYSTEMS -Vol. 53,iss. 5 (2022), s.500-509
DOI:
Digital Object Identifier (open in new tab) 10.1080/01969722.2021.2018548
Verified by:
Gdańsk University of Technology

seen 4 times

Recommended for you

Meta Tags