Home / Papers / Explainable AI (XAI): Explained

Explainable AI (XAI): Explained

15 Citations2023
G. Reddy, Y. V. P. Kumar
2023 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream)

An overview of XAI and its techniques for creating interpretable models, specifically focusing on Local Interpretable Model-Agnostic Explanations and SHapley Additive exPlanations are presented.

Abstract

Artificial intelligence (AI) has become an integral part of our lives; from the recommendations we receive on social media to the diagnoses made by medical professionals. However, as AI continues to grow more complex, the “black box” nature of many AI models has become a cause for concern. The main objective of Explainable AI (XAI) research is to produce AI models that are easily interpretable and understandable by humans. In this view, this paper presents an overview of XAI and its techniques for creating interpretable models, specifically focusing on Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). Furthermore, this paper delves into the various applications of XAI in different domains, including healthcare, finance, and law. Additionally, the ethical and legal implications of using XAI are mentioned. Finally, the paper discusses various challenges and future research directions of XAI.