Explainable Deep Learning: A Visual Analytics Approach with Transition Matrices

Pavlo Radiuk (), Olexander Barmak, Eduard Manziuk and Iurii Krak
Additional contact information
Pavlo Radiuk: Department of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, Ukraine
Olexander Barmak: Department of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, Ukraine
Eduard Manziuk: Department of Computer Science, Khmelnytskyi National University, 11 Instytuts’ka Str., 29016 Khmelnytskyi, Ukraine
Iurii Krak: Department of Theoretical Cybernetics, Taras Shevchenko National University of Kyiv, 4d Akademika Glushkova Ave, 03680 Kyiv, Ukraine

Mathematics, 2024, vol. 12, issue 7, 1-32

Abstract: The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F 1 m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems.

Keywords: explainable artificial intelligence (XAI); deep learning; machine learning; visual analytics; human-in-the-loop; model explainability; transition matrix (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/7/1024/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/7/1024/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:7:p:1024-:d:1366599

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().