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{187984,
        author = {D ROHIT KUMAR},
        title = {Black Box Neural Network: A Comparative Study of XAI Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {379-399},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187984},
        abstract = {In recent years, deep neural networks (DNNs) have become very powerful tools for solving complex problems in many areas like recognizing images, understanding language, and helping doctors with medical decisions. These networks learn from large amounts of data and make predictions that are often very accurate. However, the way they make these decisions is usually not easy to understand because they work like a "Black Box." This means we know what goes in and what comes out but not exactly how the network arrives at those results. Because of this challenge there is a growing need for explainable artificial intelligence or XAI. XAI helps us understand and explain what is happening inside these complex models. This is very important for several reasons. First, it builds trust people are more likely to use AI if they understand how decisions are made. Second, it helps developers find and fix errors in the models. Third, many industries have rules that demand explanations for automated decisions. Finally, explainability helps ensure AI systems behave fairly and ethically. By studying and comparing these methods we aim to provide a simple and clear understanding of how AI models work and to show which explanation techniques are best suited for different situations. This will help researchers, developers, and users make AI systems more transparent and trustworthy.},
        keywords = {},
        month = {November},
        }