Adding Interpretability to Neural Knowledge DNA. Issue 5 (22nd April 2022)

• Record Type: Journal Article
• Authors: Xiao, Junjie; Liu, Tao; Zhang, Haoxi; Szczerbicki, Edward
• Is Part Of: Cybernetics and systems. Volume 53:Issue 5(2022)
• Page Start: 500
• Page End: 509
• Publication Date: 2022-04-22
• Subjects: Decision trees -- deep reinforcement learning -- interpretable AI -- neural knowledge DNA; Cybernetics -- Periodicals; System theory -- Periodicals; 003.5
• DOI: 10.1080/01969722.2021.2018548
• Languages: English
• ISSNs: 0196-9722

Abstract

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.