滑铁卢大学

2023年8月8日

滑铁卢大学的研究人员已经开发出一种新的可辩解的人工智能(AI)模型来减少偏见,加强信任和准确性在机器learning-generated决策和知识的组织。传统机器学习模型往往会产生偏见的结果,有利于组织和大量人口被未知因素的影响,并从实例包含广泛的努力来识别模式和来自不同把子模式类或主要来源。医学领域是一个方面,对偏置机器学习结果有严重的影响。医院工作人员和医务人员依赖于数据集包含成千上万的医疗记录和复杂的计算机算法来对病人护理做出重要决定。机器学习是用来对数据排序,节省时间。然而,特定的病人组与罕见的症状模式可能未被发现,和贴错标签的病人和异常会影响诊断结果。这种固有的偏见和模式纠缠导致误诊和不公平的医疗结果为特定的病人组。由于安德鲁·黄博士领导的新研究,一个杰出的系统设计工程在滑铁卢,名誉教授一个创新模型旨在消除这些障碍的解决复杂的模式数据与他们特定的潜在原因影响异常和贴错标签实例。它能增强信任和可靠性可辩解的人工智能(新品)。”这项研究代表了一个新品领域的重大贡献,”黄说。“在分析大量的蛋白质绑定数据从x射线晶体学,我的团队揭示了统计蒙面的物化氨基酸交互模式和混合数据层面上由于多种因素出现在绑定的纠缠的环境。 That was the first time we showed entangled statistics can be disentangled to give a correct picture of the deep knowledge missed at the data level with scientific evidence.” This revelation led Wong and his team to develop the new XAI model called Pattern Discovery and Disentanglement (PDD). “With PDD, we aim to bridge the gap between AI technology and human understanding to help enable trustworthy decision-making and unlock deeper knowledge from complex data sources,” said Dr. Peiyuan Zhou, the lead researcher on Wong’s team. Professor Annie Lee, a co-author and collaborator from the University of Toronto, specializing in Natural Language Processing, foresees the immense value of PDD contribution to clinical decision-making. The PDD model has revolutionized pattern discovery. Various case studies have showcased PDD, demonstrating an ability to predict patients’ medical results based on their clinical records. The PDD system can also discover new and rare patterns in datasets. This allows researchers and practitioners alike to detect mislabels or anomalies in machine learning. The result shows that healthcare professionals can make more reliable diagnoses supported by rigorous statistics and explainable patterns for better treatment recommendations for various diseases at different stages. The study, Theory and rationale of interpretable all-in-one pattern discovery and disentanglement system, appears in the journal npj Digital Medicine. The recent award of an NSER Idea-to-Innovation Grant of $125 K on PDD indicates its industrial recognition. PDD is commercialized via Waterloo Commercialization Office. Journal