[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fYsWqwApRzf0ZRsOY0u798sZdseQuGYKPwxSTFaHiFqw":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":11,"question":18,"related":19,"source":29,"type":30},[],"2025-12-09 01:14:46",239483805,[8,9,10],"验证数据集","测试数据集","训练数据集",{"count":12,"courseId":13,"courseImg":14,"courseName":15,"workId":16,"workName":17},36,"67bc01e7710c495b13ee7f4af99b2458","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fb87dcbe988638ca57577336a2b61f6d4.jpeg","机器学习","work_47982785","作业2(基础回归与分类模型及应用)","下面那类数据集不参与模型权重更新和超参数优化",[20,31,40,49,52,61,70,79,88,98],{"answer":21,"createTime":5,"id":22,"options":23,"question":28,"source":29,"type":30},[],239483802,[24,25,26,27],"样本数据量较少","样本数据量较大","跟样本数据量没关系","可用的数据很少,同时模型评估又需要非常准确","简单的留出验证方法,使用于下面哪种情形( )","v1",0,{"answer":32,"createTime":5,"id":33,"options":34,"question":39,"source":29,"type":30},[],239483803,[35,36,37,38],"\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F99a9bf43eb744e9572950ff5364e6b36.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fbc485863bf6709f89c60e4fafb8e2bcd.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F6e39869f24db1fad9fa3ce91a56a3784.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F5818dbcc017fe18ae5c9ab4c0e773073.png\">","在ID3决策树算法中,信息熵的计算公式是什么",{"answer":41,"createTime":5,"id":42,"options":43,"question":48,"source":29,"type":30},[],239483804,[44,45,46,47],"2000","1980","1956","1949","达特茅斯会议是哪一年召开的",{"answer":50,"createTime":5,"id":6,"options":51,"question":18,"source":29,"type":30},[],[8,9,10],{"answer":53,"createTime":5,"id":54,"options":55,"question":60,"source":29,"type":30},[],239483806,[56,57,58,59],"softmax","sigmoid","tanh","relu","对于多分类、单标签问题,最后一层激活函数一般选用( )",{"answer":62,"createTime":5,"id":63,"options":64,"question":69,"source":29,"type":30},[],239483807,[65,66,67,68],"基尼指数","信息增益","卡方检验","信息增益比","在ID3决策树算法中,用于选择最佳划分属性的标准是什么",{"answer":71,"createTime":5,"id":72,"options":73,"question":78,"source":29,"type":30},[],239483808,[74,75,76,77],"[0,10000]","[10000,59999]","[0,9999]","[1,10000]","下面代码实现了在数据集中留出部分验证数据(validation_images,validation_labels)的操作. validation_images = train_images[:10000] train_images = train_images[10000:] validation_labels = train_labels[:10000] train_labels = train_labels[10000:] 请问验证数据集在原数据集中的索引范围是",{"answer":80,"createTime":5,"id":81,"options":82,"question":87,"source":29,"type":30},[],239483809,[83,84,85,86],"网络节点数量","Batch_size","训练轮数(epochs)","学习率(learning rate)","对于模型训练,当按照一定网络容量训练和评估完成后,在优化阶段主要是对( )进行优化",{"answer":89,"createTime":90,"id":91,"options":92,"question":97,"source":29,"type":30},[],"2025-12-02 17:00:59",239483810,[93,94,95,96],"训练数据","测试数据","验证数据","训练数据+验证数据","将数据集划分为训练数据、验证数据、测试数据,在得到网络优化参数后,需要重新训练最终的模型,这时采用的数据为( )",{"answer":99,"createTime":5,"id":100,"options":101,"question":106,"source":29,"type":30},[],239483811,[102,103,104,105],"1","0.95","0.9","0.85","已知甲乙丙三人射击命中率分别为0.5,0.6和0.5,若每人各开一枪,则目标被命中的概率_____"]