首页|Data from Mohammed V University Provide New Insights into Machine Learning (Glob al and Local Interpretability Techniques of Supervised Machine Learning Black Bo x Models for Numerical Medical Data)
Data from Mohammed V University Provide New Insights into Machine Learning (Glob al and Local Interpretability Techniques of Supervised Machine Learning Black Bo x Models for Numerical Medical Data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators publish new report on Ma chine Learning. According to news originating from Rabat, Morocco, by NewsRx cor respondents, research stated, “The most effective machine learning classificatio n techniques, such as artificial neural networks, are not easily interpretable, which limits their usefulness in critical areas, such as medicine, where errors can have severe consequences. Researchers have been working to balance the trade -off between the model performance and interpretability.” Our news journalists obtained a quote from the research from Mohammed V Universi ty, “In this study, seven interpretability techniques (global surrogate, accumul ated local effects, local interpretable model-agnostic explanations (LIME), Shap ley additive explanations (SHAP), model agnostic post hoc local explanations (MA PLE), local rule-based explanation (LORE), and Contextual Importance and Utility (CIU)) were evaluated to interpret five medical classifiers (multilayer percept ron, support vector machines, random forests, extreme gradient boosting, and nai ve bayes) using six model performance metrics and three interpretability techniq ue metrics across six medical numerical datasets. The results confirmed the effe ctiveness of integrating global and local interpretability techniques, and highl ighted the superior performance of global SHAP explainer and local CIU explanati ons.”
RabatMoroccoAfricaCyborgsEmergin g TechnologiesMachine LearningMohammed V University
NETL
NSTL
