[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fPNtogFMxMcXQscpIQcZmondPJ1vZ9GjAMpbvYw1dgCg":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":24,"type":25},[],"2025-11-22 22:55:03",239521602,[8,9,10,11],"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",{"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","RNN的核心结构中,隐藏状态(Hidden State)的主要作用是( )",[21,26,35,44,53,62,71,80,89,96],{"answer":22,"createTime":5,"id":6,"options":23,"question":19,"source":24,"type":25},[],[8,9,10,11],"v1",0,{"answer":27,"createTime":5,"id":28,"options":29,"question":34,"source":24,"type":25},[],239521603,[30,31,32,33],"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":36,"createTime":5,"id":37,"options":38,"question":43,"source":24,"type":25},[],239521604,[39,40,41,42],"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":45,"createTime":5,"id":46,"options":47,"question":52,"source":24,"type":25},[],239521605,[48,49,50,51],"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":54,"createTime":5,"id":55,"options":56,"question":61,"source":24,"type":25},[],239521606,[57,58,59,60],"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":63,"createTime":5,"id":64,"options":65,"question":70,"source":24,"type":25},[],239521607,[66,67,68,69],"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":72,"createTime":5,"id":73,"options":74,"question":79,"source":24,"type":25},[],239521608,[75,76,77,78],"完全相同","LSTM参数是SimpleRNN的4倍","SimpleRNN参数更多","不涉及权重矩阵","LSTM与SimpleRNN在参数数量上的区别是( )",{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":24,"type":25},[],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":24,"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":24,"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"]