摘要
由机器人与机器学习每日新闻的新闻记者兼工作人员新闻编辑-调查人员讨论人工智能的新发现。根据新sRx记者在西班牙塞维利亚的新闻报道，研究表明：“机器学习和深度学习在过去几年中已经成为从大型数据集中挖掘信息的最有用和最强大的工具。尽管这些基于人工智能的解决方案在许多研究领域得到了成功的应用，但众所周知，其中一些基于人工智能的解决方案被认为是黑匣子模型。”这意味着大多数专家发现很难解释和解释这些模型以及它们为什么产生这种产出。这项研究的资助者包括西班牙政府、安达卢西亚军政府、Univer Sidad Pablo de Olavide/CBUA。新闻记者从巴勃罗·德·奥拉维德大学的研究中获得了一句话：“在这种背景下，可解释人工智能应运而生，其目的是提供具有足够可解释性的黑盒模型。因此，模型易于理解和进一步应用。本文提出了一种解释黑盒模型的新方法。”利用数值关联规则对多步时间序列预测模型进行解释和解释，从而采用多目标算法从目标模型中发现定量关联规则，并应用可视化解释技术使规则更具可解释性。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in Artificial Intelligence. According to news reporting from Seville, Spain, by New sRx journalists, research stated, “Machine learning and deep learning have becom e the most useful and powerful tools in the last years to mine information from large datasets. Despite the successful application to many research fields, it i s widely known that some of these solutions based on artificial intelligence are considered black -box models, meaning that most experts find difficult to expla in and interpret the models and why they generate such outputs.” Funders for this research include Spanish Government, Junta de Andalucia, Univer sidad Pablo de Olavide/CBUA. The news correspondents obtained a quote from the research from University Pablo de Olavide, “In this context, explainable artificial intelligence is emerging w ith the aim of providing black -box models with sufficient interpretability. Thu s, models could be easily understood and further applied. This work proposes a n ovel method to explain black -box models, by using numeric association rules to explain and interpret multi -step time series forecasting models. Thus, a multi -objective algorithm is used to discover quantitative association rules from the target model. Then, visual explanation techniques are applied to make the rules more interpretable.”
NETL
NSTL