[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$flGmWxzK2Yf-CwaGD9aG_mGaiNOGg_SIPrZaitNQz7w0":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2024-04-03 09:30:53",136760028,[8,9,10,11],"RNN能够处理序列数据","RNN存在梯度消失和梯度爆炸的问题","RNN的输出只依赖于当前的输入","长短时记忆网络(LSTM)是RNN的一种改进形式",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},11,"18743194e974ecdcc3efe26de32bcfd9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F25b30343053994e8940089572d36015b.jpg","人工智能技术","work_33968827","随堂测试,2024-4-2","关于循环神经网络(RNN)的说法,错误的是",[21,32,35,44,53,62,71,80,89,98],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],136760027,[25,26,27,28],"文本属于序列数据","语音属于序列数据","时序数据属于序列数据","结构化数据属于序列数据","下列关于序列数据的处理中,错误的是","v1",0,{"answer":33,"createTime":5,"id":6,"options":34,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":36,"createTime":5,"id":37,"options":38,"question":43,"source":30,"type":31},[],136760029,[39,40,41,42],"当前时刻的输入","上一时刻的输入","当前时刻的隐藏状态","所有时刻的输入和隐藏状态","在RNN中,隐藏层的输入包括",{"answer":45,"createTime":5,"id":46,"options":47,"question":52,"source":30,"type":31},[],136760030,[48,49,50,51],"LSTM通过引入门控机制来解决梯度消失和梯度爆炸问题","LSTM包括输入门、遗忘门和输出门","LSTM的内部状态(细胞状态)在不同的时间步中保持不变","LSTM能够有效地学习长距离依赖关系","关于LSTM网络的说法,错误的是",{"answer":54,"createTime":5,"id":55,"options":56,"question":61,"source":30,"type":31},[],136760031,[57,58,59,60],"使用更小的学习率","使用更深的网络结构","使用梯度剪裁","使用批量归一化","在训练RNN时,以下哪种方法可以缓解梯度消失和梯度爆炸问题",{"answer":63,"createTime":5,"id":64,"options":65,"question":70,"source":30,"type":31},[],136760032,[66,67,68,69],"GRU是LSTM的一种简化版本","GRU包括更新门和重置门","GRU的内部状态在不同的时间步中保持不变","GRU能够有效地学习长距离依赖关系","关于门控循环单元(GRU)的说法,错误的是",{"answer":72,"createTime":5,"id":73,"options":74,"question":79,"source":30,"type":31},[],136760033,[75,76,77,78],"梯度消失","梯度爆炸","神经元失效","过拟合","在训练RNN时,如果使用ReLU作为激活函数,可能会出现的问题是",{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":30,"type":31},[],136760034,[84,85,86,87],"BiRNN同时考虑了序列的前向和后向信息","BiRNN的输出是前向和后向隐藏层的输出的拼接","BiRNN可以用于提高序列预测的准确性","BiRNN的训练时间比单向RNN长一倍","关于双向RNN(BiRNN)的说法,错误的是",{"answer":90,"createTime":5,"id":91,"options":92,"question":97,"source":30,"type":31},[],136760035,[93,94,95,96],"池化","填充","卷积","批量归一化","在RNN中,以下哪种技术可以用来处理不同长度的序列数据",{"answer":99,"createTime":5,"id":100,"options":101,"question":105,"source":30,"type":31},[],136760036,[102,96,103,104],"dropout","L1正则化","B和C都是正确的","在使用RNN进行语言模型训练时,以下哪种技术可以减少模型的过拟合问题"]