[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fTd3_-Q1SdtcgeWY24rJoSaKhB4WfgTMR15Yk_DrBcno":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2025-12-22 13:19:53",279872270,[8,9,10,11],"GPU带来的算力提升","海量训练数据的积累","ReLU激活函数的提出","量子计算机的普及",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},54,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","40576b98a38c4d19ab2e0fd7228b7697","第四章 深度学习测试题(补充)","以下哪项不是深度学习快速发展的关键条件( )",[21,32,35,44,53,62,71,80,89,98],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],279872268,[25,26,27,28],"基于浅层神经网络的机器学习方法","基于深层神经网络的机器学习方法","仅处理图像数据的人工智能技术","无需训练数据的端到端学习方法","深度学习的核心定义是( )","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},[],279872273,[39,40,41,42],"卷积","池化","全连接","注意力机制","卷积神经网络(CNN)的核心操作不包括( )",{"answer":45,"createTime":5,"id":46,"options":47,"question":52,"source":30,"type":31},[],279872275,[48,49,50,51],"静态图像数据","序列相关数据","结构化表格数据","无标签聚类数据","循环神经网络(RNN)主要用于处理哪种类型的数据( )",{"answer":54,"createTime":5,"id":55,"options":56,"question":61,"source":30,"type":31},[],279872277,[57,58,59,60],"卷积核","池化层","门控机制","全连接层","长短记忆网络(LSTM)通过什么结构解决RNN的梯度消失问题( )",{"answer":63,"createTime":5,"id":64,"options":65,"question":70,"source":30,"type":31},[],279872279,[66,67,68,69],"输入门","遗忘门","输出门","记忆门","LSTM中,负责决定遗忘多少之前长期记忆的是( )",{"answer":72,"createTime":5,"id":73,"options":74,"question":79,"source":30,"type":31},[],279872280,[75,76,77,78],"SGD","Adam","RMSprop","梯度下降","以下哪种优化器结合了动量和自适应学习率调整( )",{"answer":81,"createTime":5,"id":82,"options":83,"question":88,"source":30,"type":31},[],279872282,[84,85,86,87],"训练数据集的总样本数","每次参数更新使用的样本数","验证数据集的样本数","测试数据集的样本数","深度学习中,"批次大小(Batch Size)"指的是( )",{"answer":90,"createTime":5,"id":91,"options":92,"question":97,"source":30,"type":31},[],279872284,[93,94,95,96],"L1正则化","L2正则化","Dropout","数据增强","用于减少模型对特定神经元依赖、防止过拟合的正则化方法是( )",{"answer":99,"createTime":5,"id":100,"options":101,"question":106,"source":30,"type":31},[],279872286,[102,103,104,105],"一次参数更新","整个训练数据集完整通过网络一次","一个批次样本的训练","一次验证过程","一个"epoch"在深度学习训练中表示( )"]