[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fgMYdDacv8ueuMjt6V0-gqNeDetYztWg8UlqZjG7mcCU":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2024-11-25 10:43:24",167337398,[8,9,10,11],"前向计算","反向计算梯度","更新参数","选择损失函数",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},20,"de5c51822504c862fca74c1d33d8c654","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Ffb4e0e6a5574c0a2bea5a3691ff957f7.jpg","深度学习原理与项目实战","work_39225152","新建作业20241120085842","以下哪个不是反向传播算法的步骤",[21,32,41,50,59,68,75,84,93,102],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],167337387,[25,26,27,28],"卷积神经网络","循环神经网络","多层感知器","生成对抗网络","前馈神经网络(FNN)也被称为什么","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],167337388,[36,37,38,39],"增加计算复杂度","引入非线性","减少训练时间","增加模型的参数数量","激活函数在神经网络中的作用是什么",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],167337389,[45,46,47,48],"Sigmoid","ReLU","Tanh","Mean","以下哪个不是常见的激活函数",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],167337390,[54,55,56,57],"计算效率高","缓解梯度消失问题","输出中心化","生物学合理性","ReLU函数的优点不包括以下哪一项",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],167337391,[63,64,65,66],"死亡ReLU问题","非负输入限制","输出有界","数值稳定性问题","以下哪个问题不是ReLU函数的缺点",{"answer":69,"createTime":5,"id":70,"options":71,"question":74,"source":30,"type":31},[],167337392,[45,47,72,73],"Leaky ReLU","Softmax","以下哪个是ReLU的变种",{"answer":76,"createTime":5,"id":77,"options":78,"question":83,"source":30,"type":31},[],167337393,[79,80,81,82],"多层结构","前馈","循环","非线性激活","以下哪个不是前馈神经网络的关键特点",{"answer":85,"createTime":5,"id":86,"options":87,"question":92,"source":30,"type":31},[],167337394,[88,89,90,91],"神经网络可以近似任何函数","神经网络只能近似线性函数","神经网络不能近似非线性函数","神经网络只能近似连续函数","通用近似定理说明了什么",{"answer":94,"createTime":5,"id":95,"options":96,"question":101,"source":30,"type":31},[],167337395,[97,98,99,100],"梯度下降","数据增强","特征选择","数据清洗","在神经网络中,参数学习通常涉及以下哪个过程",{"answer":103,"createTime":5,"id":104,"options":105,"question":110,"source":30,"type":31},[],167337396,[106,107,108,109],"标量关于向量的偏导数","向量关于向量的偏导数(雅克比矩阵)","向量关于矩阵的偏导数","矩阵的行列式","以下哪个不是矩阵微积分中的基本概念"]