Paper Title :Illuminating The Black Box: Explainable AI (XAI)
Author :Ansh Tandon, Rajeel Ansari, Chahat Tandon, Rohan Shah, Ashok Saranya
Article Citation :Ansh Tandon ,Rajeel Ansari ,Chahat Tandon ,Rohan Shah ,Ashok Saranya ,
(2024 ) " Illuminating The Black Box: Explainable AI (XAI) " ,
International Journal of Advance Computational Engineering and Networking (IJACEN) ,
pp. 21-27,
Volume-12,Issue-3
Abstract : In recent years, the field of artificial intelligence (AI) has witnessed unprecedented growth, leading
to significant advancements in various sectors such as healthcare, finance, and autonomous systems. However,
this growth has also brought to light the complexities and opacities of AI models, especially deep learning
algorithms, which often function as 'black boxes.' Explainable Artificial Intelligence (XAI) has emerged as a
crucial subfield, aiming to make AI decisions transparent, understandable, and trustworthy for human users.
This paper presents a comprehensive survey of the current state of XAI. It begins by exploring the fundamental
concepts and methodologies underpinning XAI, including feature attribution, model visualization, and localglobal
explanations. The paper then delves into domain-specific applications of XAI, highlighting how
explainability is being integrated in areas such as healthcare diagnostics, financial decision-making, and legal
systems. Furthermore, the survey addresses the ethical implications and challenges in implementing XAI, such
as balancing transparency with model complexity and maintaining privacy and security. In the latter part, the
paper forecasts future trends and potential avenues in XAI research. These include the development of
standardized evaluation metrics for explanations, the integration of causal inference for more insightful
explanations, the rise of user-centric explanation interfaces, and the potential regulatory landscape shaping the
adoption of XAI. By providing a holistic view of the current achievements and potential future directions, this
paper aims to guide researchers, practitioners, and policymakers in the evolving landscape of explainable AI.
Keywords - AI Transparency, Machine Learning Interpretability, Explainable Artificial Intelligence (XAI)
Type : Research paper
Published : Volume-12,Issue-3
DOIONLINE NO - IJACEN-IRAJ-DOIONLINE-20639
View Here
Copyright: © Institute of Research and Journals
|
![](images/permissions-active.png) |
| |
![](images/pdf_icon.png) |
PDF |
| |
Viewed - 6 |
| |
Published on 2024-06-26 |
|