Academic Journal

Understanding explainable artificial intelligence techniques: a comparative analysis for practical application

التفاصيل البيبلوغرافية
العنوان: Understanding explainable artificial intelligence techniques: a comparative analysis for practical application
المؤلفون: Bhatnagar, Shweta, Agrawal, Rashmi
المساهمون: NA
المصدر: Bulletin of Electrical Engineering and Informatics; Vol 13, No 6: December 2024; 4451-4455 ; 2302-9285 ; 2089-3191 ; 10.11591/eei.v13i6
بيانات النشر: Institute of Advanced Engineering and Science
سنة النشر: 2024
مصطلحات موضوعية: Computer Applications, Explainable artificial intelligence, Explainable artificial intelligence models, Explainable artificial intelligence techniques, Local interpretable model-agnostic explanations, Shapley additive explanations
الوصف: Explainable artificial intelligence (XAI) uses artificial intelligence (AI) tools and techniques to build interpretability in black-box algorithms. XAI methods are classified based on their purpose (pre-model, in-model, and post-model), scope (local or global), and usability (model-agnostic and model-specific). XAI methods and techniques were summarized in this paper with real-life examples of XAI applications. Local interpretable model-agnostic explanations (LIME) and shapley additive explanations (SHAP) methods were applied to the moral dataset to compare the performance outcomes of these two methods. Through this study, it was found that XAI algorithms can be custom-built for enhanced model-specific explanations. There are several limitations to using only one method of XAI and a combination of techniques gives complete insight for all stakeholders.
نوع الوثيقة: article in journal/newspaper
وصف الملف: application/pdf
اللغة: English
Relation: https://beei.org/index.php/EEI/article/view/8378/3986; https://beei.org/index.php/EEI/article/view/8378
DOI: 10.11591/eei.v13i6.8378
الاتاحة: https://beei.org/index.php/EEI/article/view/8378
https://doi.org/10.11591/eei.v13i6.8378
Rights: Copyright (c) 2024 Institute of Advanced Engineering and Science ; https://creativecommons.org/licenses/by-sa/4.0
رقم الانضمام: edsbas.5772856
قاعدة البيانات: BASE