Explainable AI (XAI): Making Machine Learning Models Transparent |
Author(s): |
| Aniket Omkarnath Gaud , Tilak Maharashtra Vidyapeeth, Pune |
Keywords: |
| Explainable AI (XAI), Machine Learning, Interpretability, Transparency, Trust, Ethical AI, Model Explainability, User-Centered Explanations, Evaluation Metrics, Domain-Specific Models |
Abstract |
|
This research explores Explainable Artificial Intelligence (XAI), focusing on techniques that make complex machine learning models transparent and understandable. As AI systems become more widespread, ensuring that their decisions are interpretable is essential for trust, fairness, and ethical deployment. This study reviews recent advancements in XAI, highlights major limitations faced by researchers, discusses strategies used to overcome these issues, and presents key findings to pave the way for future innovations. Furthermore, it introduces novel perspectives on integrating XAI with evolving AI technologies, including Federated Learning, Reinforcement Learning, and Autonomous Systems, to enhance model interpretability and trustworthiness. |
Other Details |
|
Paper ID: IJSRDV13I30115 Published in: Volume : 13, Issue : 3 Publication Date: 01/06/2025 Page(s): 144-146 |
Article Preview |
|
|
|
|
