[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fY2WTzQtBaBeMF__gCBO5FHC6eOyal1Lw8M5_6gA1ess":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2025-11-22 22:55:03",239521608,[8,9,10,11],"完全相同","LSTM参数是SimpleRNN的4倍","SimpleRNN参数更多","不涉及权重矩阵",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},21,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","work_48082556","第九次课后练习","LSTM与SimpleRNN在参数数量上的区别是( )",[21,32,41,50,59,68,77,80,89,96],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],239521602,[25,26,27,28],"存储当前输入","存储序列的历史信息","直接输出预测结果","计算梯度值","RNN的核心结构中,隐藏状态(Hidden State)的主要作用是( )","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],239521603,[36,37,38,39],"序列长度过短","激活函数线性化","长期依赖导致梯度在反向传播中指数衰减","参数矩阵维度过大","RNN在训练中容易出现的梯度消失问题的主要原因是( )",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],239521604,[45,46,47,48],"单一激活函数","门控机制","固定大小输入","卷积层","LSTM网络为了解决RNN的梯度消失问题,引入了( )",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],239521605,[54,55,56,57],"决定新信息的添加","控制输出状态","决定遗忘先前细胞状态的信息","直接生成隐藏状态","在LSTM的三大门控机制中,遗忘门的主要作用是( )",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],239521606,[63,64,65,66],"固定输出大小","共享参数处理变长序列","忽略时间依赖","仅处理图像数据","RNN处理序列数据时,使用循环结构的主要优势是( )",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":30,"type":31},[],239521607,[72,73,74,75],"产生高维稀疏向量,便于词频统计","直接生成稠密嵌入","忽略词汇表大小","加速梯度爆炸","文本数据预处理中,向量化表示常用one-hot编码的原因是( )",{"answer":78,"createTime":5,"id":6,"options":79,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":30,"type":31},[],239521609,[84,85,86,87],"机器翻译","情感分析","固定尺寸图像分类","文本生成","RNN的应用领域不包括( )",{"answer":90,"createTime":91,"id":92,"options":93,"question":94,"source":30,"type":95},[],"2025-11-22 22:57:39",239522519,[],"LSTM网络的三大门控分别是 ____门、 ____门和 ____门",2,{"answer":97,"createTime":91,"id":98,"options":99,"question":100,"source":30,"type":95},[],239522520,[],"文本预处理中,序列对齐常用 ____技术处理变长序列,如填充至固定长度"]