[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fUXLM_FAWoldGFPA6gkXEkVxKe4eV8P0NQNywXc_KnhQ":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":94},[],"2023-05-26 12:32:38",30359066,[8,9,10,11],"误差","偏差","方差","噪声",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},10,"389d90925225b2f9a0f56a961912042d","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F442bc29caf6a5b7a43ab9702398ec490.jpg","数据分析","a22d59084fb944da96c3da06e75b4cbd","开发班作业三","泛化错误率由哪三个构成()",[21,32,40,49,58,67,76,85,95,104],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],30359057,[25,26,27,28],"学习误差","经验误差","测试误差","检验误差","学习器在训练集上的误差称为"训练误差"或(),在新样本上的误差称为"泛化误差"","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":39,"source":30,"type":31},[],30359058,[36,37,38,26],"欠拟合","泛化误差","过拟合","模型把数据学习的太彻底,以至于把噪声数据的特征也学习到了,这样就会导致在后期测试的时候不能够很好地识别数据,模型泛化能力太差,这是()的原因",{"answer":41,"createTime":5,"id":42,"options":43,"question":48,"source":30,"type":31},[],30359059,[44,45,46,47],"数据集","测试集","模型集","训练集","通常,我们可通过实验测试来对学习器的泛化误差进行评估并进而做出选择.为此,需使用一个()来测试学习期对新样本的判别能力",{"answer":50,"createTime":5,"id":51,"options":52,"question":57,"source":30,"type":31},[],30359060,[53,54,55,56],"性能度量是衡量模型泛化能力的评价标准,反映了任务需求","在对比不同模型的能力时,使用不同的性能度量会导致不同的评判结果,这就意味着模型的"好坏"是相对的","回归任务最常用的性能度量是"均方误差"","性能度量实用意义不大","关于性能度量不正确的是()",{"answer":59,"createTime":5,"id":60,"options":61,"question":66,"source":30,"type":31},[],30359061,[62,63,64,65],"光滑非单调","非光滑非单调","非光滑单调","光滑单调","P-R图一般为()曲线",{"answer":68,"createTime":5,"id":69,"options":70,"question":75,"source":30,"type":31},[],30359062,[71,72,73,74],"查准率\u002F准确率(precision): P = TP\u002F(TP-FP)","查准率(precision):被认定为正例的里面,判断正确的比例","查全率\u002F召回率\u002F灵敏度(recall):R = TP\u002F(TP+FN)","查全率(recall):真实正例里,被判断出为正例的比例","下列错误的是()",{"answer":77,"createTime":5,"id":78,"options":79,"question":84,"source":30,"type":31},[],30359063,[80,81,82,83],"训练误差是指模型在训练集上的错分样本比率,说白了就是在训练集上训练完毕后在训练集本身上进行预测得到了错分率","泛化误差是指模型在未知记录上的期望误差,说白了就是在训练集上没见过的数据的错分样本比率","在样本集划分时,如果得到的训练集与测试集的数据没有交集,此时测试误差基本等同于泛化误差","偏差大:拟合不足\u002F过拟合;方差大:欠拟合","下列说法不正确的是()",{"answer":86,"createTime":5,"id":87,"options":88,"question":93,"source":30,"type":94},[],30359064,[89,90,91,92],"评估方法.如何获得测试结果","性能度量.如何评估性能优劣","比较检验.如何判断实质差别","实施分析.如何更快更好实施","模型选择有哪三个关键问题()",1,{"answer":96,"createTime":5,"id":97,"options":98,"question":103,"source":30,"type":94},[],30359065,[99,100,101,102],"留出法","交叉验证法","采样法","自助法","常见的评估方法有()",{"answer":105,"createTime":5,"id":6,"options":106,"question":19,"source":30,"type":94},[],[8,9,10,11]]