Deep learning models have been successfully applied in many fields, but as they are inherently black-box functions, their interpretability and trustworthiness are very limited. Explainable AI (XAI) has been developed to overcome these problems of interpretability, bringing more transparency and understandability to AI models. Fuzzy Logic is one of the approaches that can bridge the gap between machine learning and human reasoning systems making it a very powerful tool which makes AI systems more interpretable. The focus of this paper is to combine fuzzy logic in deep learning and gain explainability without compromising predictive performance. We review several explainable fuzzy logic paradigms and discuss how they offer a unique solution to the model interpretability problem by creating a link between AI decision-making and human-readable rationale. Using fuzzy logic to enhance deep learning can provide improved performance (when designed correctly) with better understanding of how the model works compared to traditional deep learning models due to the transparent nature of the fuzzy logic system. We also discuss the applications of explainable fuzzy logic in sensitive areas like healthcare, finance, and autonomous systems where trust and transparency are critical. It also identifies the challenges to be addressed and future research directions in building fuzzy-enhanced explainable AI frameworks. Fuzzy logic-based approaches to decision-making can help AI systems deliver more interpretable and trustable outcomes, thus increasing their adoption in high-impact areas. The research outcomes help develop explainability within AI systems, thus leading to the deployment of AI in a more ethical and responsible manner.
Explainable AI, Fuzzy Logic, Deep Learning, Model Interpretability, Trustworthy AI, Transparency in AI.
The authors confirm contribution to the paper as follows:
Conceptualization: Yassir Farooqui, Kishori Shekokar, Pooja Bhatt and Kiran Macwan; Writing- Original Draft Preparation: Yassir Farooqui, Kishori Shekokar, Pooja Bhatt and Kiran Macwan; Visualization: Yassir Farooqui and Kishori Shekokar; Investigation: Pooja Bhatt and Kiran Macwan; Supervision: Yassir Farooqui and Kishori Shekokar; Validation: Pooja Bhatt and Kiran Macwan; Writing- Reviewing and Editing: Yassir Farooqui, Kishori Shekokar, Pooja Bhatt and Kiran Macwan; All authors reviewed the results and approved the final version of the manuscript.
We would like to thank Reviewers for taking the time and effort necessary to review the manuscript. We sincerely appreciate all valuable comments and suggestions, which helped us to improve the quality of the manuscript.
No funding was received to assist with the preparation of this manuscript.
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Data sharing is not applicable to this article as no new data were created or analysed in this study.
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Yassir Farooqui, Kishori Shekokar, Pooja Bhatt and Kiran Macwan, “Explainable Fuzzy Logic in AI: Enhancing Transparency and Trust in Deep Learning Models”, Journal of Machine and Computing, vol.5, no.4, pp. 2241-2253, October 2025, doi: 10.53759/7669/jmc202505174.
© 2025 Yassir Farooqui, Kishori Shekokar, Pooja Bhatt and Kiran Macwan. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
