[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fqXC_mPcj4MW913WCdnRynndtH7iEueE6FH0SGIVZl_w":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":16,"related":17,"source":27,"type":28},[],"2023-12-10 21:23:39",112790096,[8,9,10,11],"训练误差和验证误差都很高","训练误差高,验证误差低","训练误差低,验证误差高","训练误差和验证误差都很低",{"courseId":13,"courseImg":14,"courseName":15},"f20e2428c31261e30db352a88a06084e","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F25b30343053994e8940089572d36015b.jpg","机器学习","以下哪个是过拟合的一个例子",[18,29,38,45,54,57,64,72,78,86],{"answer":19,"createTime":5,"id":20,"options":21,"question":26,"source":27,"type":28},[],112790089,[22,23,24,25],"输入层","隐藏层","输出层","感知层","以下哪个不是神经网络中的层","v1",0,{"answer":30,"createTime":5,"id":31,"options":32,"question":37,"source":27,"type":28},[],112790091,[33,34,35,36],"训练神经网络","预测新实例","两者都是","两者都不是","前向传播是在哪个过程中进行的",{"answer":39,"createTime":5,"id":40,"options":41,"question":44,"source":27,"type":28},[],112790094,[42,43,35,36],"更新权重和偏差以最小化代价函数","前向传播输入到输出","反向传播是用于",{"answer":46,"createTime":5,"id":47,"options":48,"question":53,"source":27,"type":28},[],112790095,[49,50,51,52],"批量梯度下降每次使用整个训练集,而随机梯度下降每次使用一个样本","批量梯度下降每次使用一个样本,而随机梯度下降每次使用整个训练集","两者没有区别","以上都不是","批量梯度下降和随机梯度下降的主要区别是什么",{"answer":55,"createTime":5,"id":6,"options":56,"question":16,"source":27,"type":28},[],[8,9,10,11],{"answer":58,"createTime":5,"id":59,"options":60,"question":63,"source":27,"type":28},[],112790099,[61,62,35,36],"过拟合","欠拟合","Dropout是用于防止什么现象的",{"answer":65,"createTime":5,"id":66,"options":67,"question":71,"source":27,"type":28},[],112790101,[68,69,70,52],"每次更新权重时的步长","训练集的大小","神经网络的层数","什么是学习率",{"answer":73,"createTime":5,"id":74,"options":75,"question":77,"source":27,"type":28},[],112790104,[22,24,23,76],"数据层","下列哪项不属于神经网络的基本组成部分",{"answer":79,"createTime":5,"id":80,"options":81,"question":85,"source":27,"type":28},[],112790105,[82,83,84,36],"批量梯度下降","随机梯度下降","两者都有","在训练神经网络时,我们通常使用的方法是",{"answer":87,"createTime":88,"id":89,"options":90,"question":94,"source":27,"type":28},[],"2023-12-10 21:23:40",112790106,[91,92,93,52],"用于在神经网络中引入非线性的函数","用于在神经网络中计算误差的函数","用于在神经网络中调整权重的函数","什么是激活函数"]