Evaluating explainable artificial intelligence (XAI): algorithmic explanations for transparency and trustworthiness of ML algorithms and AI systems
Evaluating explainable artificial intelligence (XAI): algorithmic explanations for transparency and trustworthiness of ML algorithms and AI systems
复制标题
评估可解释人工智能 (XAI)：机器学习算法和人工智能系统透明度和可信度的算法解释
DOI：
10.1117/12.2620598
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Rawat, Danda B.
中科院分区：
文献类型：
--
作者：
Khakurel, Utsab B.;Rawat, Danda B.
可解释人工智能（XAI）是解释机器学习（ML）算法所做选择背后的推理的能力，它可以帮助理解和保持ML算法决策能力的透明度。人类在生活中每天都要做出成千上万的决定。每个人做出的每一个决定，他们都可以解释他们做出这些选择的原因。然而，ML和AI系统的情况并不相同。此外，XAI并没有被广泛研究，直到突然这个话题被提出来，并且已经成为人工智能中最相关的话题之一，以获得可信和透明的结果。XAI试图通过回答有关模型如何有效地得出输出的问题来为ML算法提供最大的透明度。使用XAI的ML模型将能够解释结果背后的原理，了解学习模型的弱点和优势，并能够看到模型在未来的表现。在本文中，我们研究了XAI算法的可信度和透明度。我们使用一些示例用例和SHAP（SHapley Additive ExPlanations）库来评估XAI，并在预测过程中单独和累积地可视化特征的效果。
Explainable Artificial Intelligence (XAI) is the capability of explaining the reasoning behind the choices made by the machine learning (ML) algorithm which can help understand and maintain the transparency of the decision-making capability of the ML algorithm. Humans make thousands of decisions every day in their lives. Every decision an individual makes, they can explain the reasons behind why they made the choices that they made. Nonetheless, it is not the same in the case of ML and AI systems. Furthermore, XAI was not wideley researched until suddenly the topic was brought forward and has been one of the most relevant topics in AI for trustworthy and transparent outcomes. XAI tries to provide maximum transparency to a ML algorithm by answering questions about how models effectively came up with the output. ML models with XAI will have the ability to explain the rationale behind the results, understand the weaknesses and strengths the learning models, and be able to see how the models will behave in the future. In this paper, we investigate XAI for algorithmic trustworthiness and transparency. We evaluate XAI using some example use cases and by using SHAP (SHapley Additive exPlanations) library and visualizing the effect of features individually and cumulatively in the prediction process.
DOI：
10.1109/globecom46510.2021.9685333
发表时间：
2021-12
期刊：
2021 IEEE Global Communications Conference (GLOBECOM)
影响因子：
--
作者：
Bimal Ghimire;D. Rawat;A. Rahman
通讯作者：
Bimal Ghimire;D. Rawat;A. Rahman
DOI：
10.1073/pnas.1900654116
发表时间：
2019-10-29
影响因子：
11.1
作者：
Murdoch, W. James;Singh, Chandan;Yu, Bin
通讯作者：
Yu, Bin