Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202936,
        author = {Nirmala Bachate and Mansi Kudalkar and Dr. Manisha Bhanuse},
        title = {Hybrid Explainable AI Models for Robust Pattern Recognition in High-Stakes Applications},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10743-10744},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202936},
        abstract = {Pattern recognition systems powered by deep learning have achieved remarkable success in domains such as medical imaging, speech recognition, and cybersecurity. However, their black-box nature limits transparency, accountability, and trust, especially in high-stakes environments. This paper explores the integration of explainable AI (XAI) techniques into pattern recognition, focusing on hybrid models that combine deep learning with symbolic reasoning. Case studies in medical imaging and adversarial defence illustrate how XAI-driven recognition systems can enhance interpretability, robustness, and ethical accountability.},
        keywords = {},
        month = {May},
        }