Research from Boston University Broadens Understanding of Machine Learning (DREA MER: a computational framework to evaluate readiness of datasets for machine lea rning)
Research from Boston University Broadens Understanding of Machine Learning (DREA MER: a computational framework to evaluate readiness of datasets for machine lea rning)
波士顿大学的研究扩大了对机器学习的理解(DREA MER:评估机器学习数据集准备情况的计算框架)
扫码查看
点击上方二维码区域，可以放大扫码查看
摘要
由一名新闻记者-机器人与机器学习每日新闻编辑-研究人员详细介绍了人工智能的新数据。根据NewsRx J ournalists在波士顿大学的新闻报道，研究表明：“机器学习(ML)已经成为分析跨不同领域大规模数据集的首选计算范式。”这项研究的资助者包括国家卫生研究院。新闻记者从波士顿大学的研究中获得了一句话:“数据集质量的评估是成功部署ML模型的关键先导。在这项研究中,我们引入了DREAMER(Data REAdine SS for MachinE Learning Research),DREAMER是GitHub和Docker上公开访问的工具,便于在研究界采用和进一步完善.本文提出的模型应用于三个不同的表格数据集.通过已建立的数据质量指标评估，结果在ML任务准备方面的质量显著提高。我们的发现证明了该框架在大幅提高原始数据集质量方面的有效性，这是通过排除无关特征和行实现的。这种改进提高了监督和非监督学习方法的准确性。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Researchers detail new data in artific ial intelligence. According to news reporting from Boston University by NewsRx j ournalists, research stated, "Machine learning (ML) has emerged as the predomina nt computational paradigm for analyzing large-scale datasets across diverse doma ins." Funders for this research include National Institutes of Health. The news correspondents obtained a quote from the research from Boston Universit y: "The assessment of dataset quality stands as a pivotal precursor to the succe ssful deployment of ML models. In this study, we introduce DREAMER (Data REAdine ss for MachinE learning Research), an algorithmic framework leveraging supervise d and unsupervised machine learning techniques to autonomously evaluate the suit ability of tabular datasets for ML model development. DREAMER is openly accessib le as a tool on GitHub and Docker, facilitating its adoption and further refinem ent within the research community.. The proposed model in this study was applied to three distinct tabular datasets, resulting in notable enhancements in their quality with respect to readiness for ML tasks, as assessed through established data quality metrics. Our findings demonstrate the efficacy of the framework in substantially augmenting the original dataset quality, achieved through the elim ination of extraneous features and rows. This refinement yielded improved accura cy across both supervised and unsupervised learning methodologies."
Key words
Boston University/Cyborgs/Emerging Tec hnologies/Machine Learning
NETL
NSTL