[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f1VAtI91zTKQNzBDk9pAvTO1qfC8AVeyVxEOQsZs0SxU":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2025-03-27 16:08:27",180502091,[8,9,10,11],"0.2","0.5","0.8","0.6",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},10,"f20e2428c31261e30db352a88a06084e","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F25b30343053994e8940089572d36015b.jpg","机器学习","39ecb729a4854f84a122aa7703bf1069","第二章-模型评估与选择","假设我们有一个二分类模型,其真正例率(TPR)为 0.8,假正例率(FPR)为 0.2,那么该模型的 ROC 曲线下的面积(AUC)为( )",[21,32,41,50,59,67,76,83,86,95],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],180502084,[25,26,27,28],"真正例(TP)","假正例(FP)","真反例(TN)","假反例(FN)","在评估分类模型时,若一个样本实际为正类,被预测为正类,这属于( )","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],180502085,[36,37,38,39],"准确率","召回率","梯度下降","F1 值","以下不属于性能度量的是( )",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],180502086,[45,46,47,48],"1:9","3:7","7:3","9:1","当我们使用留出法将数据集划分为训练集和测试集时,通常训练集和测试集的比例为( )",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],180502087,[54,55,56,57],"k 折交叉验证中,k 值越大,评估结果越稳定","留一法是 k 折交叉验证的特殊情况,其中 k 等于样本数","交叉验证法可以有效避免过拟合","分层采样可以保证每个折叠中的样本类别比例与原始数据集一致","以下关于交叉验证法的说法,错误的是( )",{"answer":60,"createTime":5,"id":61,"options":62,"question":66,"source":30,"type":31},[],180502088,[36,63,64,65],"查准率","ROC 曲线下的面积(AUC)","错误率","若分类任务中各类别的样本数量严重不均衡,以下哪种性能度量更能反映模型的性能?( )",{"answer":68,"createTime":5,"id":69,"options":70,"question":75,"source":30,"type":31},[],180502089,[71,72,73,74],"混淆矩阵只能用于二分类问题","混淆矩阵中对角线元素之和等于样本总数","混淆矩阵可以直观地展示模型的分类情况","混淆矩阵的行数和列数一定不相等","以下关于混淆矩阵的说法正确的是( )",{"answer":77,"createTime":5,"id":78,"options":79,"question":82,"source":30,"type":31},[],180502090,[80,81,37,36],"均方误差(MSE)","精确率","在回归任务中,常用的性能度量是( )",{"answer":84,"createTime":5,"id":6,"options":85,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":87,"createTime":5,"id":88,"options":89,"question":94,"source":30,"type":31},[],180502092,[90,91,92,93],"增加训练数据","降低模型复杂度","早停法","增加模型参数","以下哪种方法不是用来缓解过拟合的( )",{"answer":96,"createTime":5,"id":97,"options":98,"question":103,"source":30,"type":31},[],180502093,[99,100,101,102],"可以根据模型在验证集上的性能来选择模型","模型选择的目标是找到在测试集上性能最好的模型","信息准则可以用于模型选择","模型选择只需要考虑模型的训练误差","以下关于模型选择的说法,错误的是( )"]