[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fvsqDNk405eiGbLGiUEPydfuVbfbnSU1TW8PysBwrprM":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":18,"related":19,"source":27,"type":32},[],"2023-05-07 18:17:27",83412574,[8,9,10,11],"\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F50e9fb5be87441eedf8d143b563cedc8.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fedd598366df89d37e49746c39bfc1e06.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F70f8db469afb63b0b80d01cd09b3015d.png\">","\u003Cimg src=\"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Fa85b4f6e7912af8e993b68c49ce963f8.png\">",{"courseId":13,"courseImg":14,"courseName":15,"workId":16,"workName":17},"1000062238","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F165f6325b4bc8a1756576288f56bd7e7.jpg","大数据解析与应用导论","27347261","第八章单元测试","下面哪个函数不是神经元的激活函数( )",[20,29,33,42,52],{"answer":21,"createTime":5,"id":22,"options":23,"question":26,"source":27,"type":28},[],83412573,[24,25],"对","错","为了提高预测结果的精度,网络结构设置得越复杂越好,不必考虑训练网络时所花费的时间.( )","v2",3,{"answer":30,"createTime":5,"id":6,"options":31,"question":18,"source":27,"type":32},[],[8,9,10,11],0,{"answer":34,"createTime":5,"id":35,"options":36,"question":41,"source":27,"type":32},[],83412575,[37,38,39,40],"CNN由卷积层、池化层和全连接层组成,常用于处理与图像有关的问题","由于卷积核的大小一般是3*3或更大,因此卷积层得到的特征图像一定比原图像小","CNN中的池化层用于降低特征图维数,以避免过拟合","CNN中的全连接层常用softmax作为激活函数","关于卷积神经网络CNN,以下说法错误的是:( )",{"answer":43,"createTime":5,"id":44,"options":45,"question":50,"source":27,"type":51},[],83412576,[46,47,48,49],"输入门","输出门","更新门","遗忘门","相较于传统RNN,LSTM引入了独特的门控机制.以下哪些是LSTM中包含的门结构:( )",1,{"answer":53,"createTime":5,"id":54,"options":55,"question":60,"source":27,"type":51},[],83412577,[56,57,58,59],"CNN适用于图像处理,而RNN适用于序列数据处理","CNN和RNN都属于神经网络,因此二者的训练方式完全一致,均采用BP算法","CNN和RNN都采用了权值共享机制以减少网络中的参数量","在同一个网络中,CNN结构和RNN结构不能同时使用","关于卷积神经网络CNN与循环神经网络RNN,下面说法正确的有:( )"]