[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fPJqNrs3sFLaKlPIWycJ2mHXA-WCOPW5Ncg0Qr2vGIP0":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2026-05-02 11:44:10",353681040,[8,9,10,11],"提高模型的泛化能力","捕获更多图像中的细节信息","简化模型结构","减少数据预处理时间",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},83,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","work_52928797","第5章 经典卷积神经网络(上)(作业)","哪个选项不是数据增强可能带来的好处",[21,32,40,43,52,61,70,79,88,97],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],353681038,[25,26,27,28],"2014年","2012年","2015年","2013年","VGGNet是在哪一年由牛津大学计算机视觉组和Google DeepMind公司研究员共同研发出来的","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":39,"source":30,"type":31},[],353681039,[36,8,37,38],"降低特征图的维度","减少模型参数","增加模型的非线性","VGGNet中的池化层主要用于什么目的",{"answer":41,"createTime":5,"id":6,"options":42,"question":19,"source":30,"type":31},[],[8,9,10,11],{"answer":44,"createTime":5,"id":45,"options":46,"question":51,"source":30,"type":31},[],353681041,[47,48,49,50],"使用LRN","Dropout","增加网络深度","增大卷积核大小","AlexNet使用哪种方式来避免过拟合",{"answer":53,"createTime":5,"id":54,"options":55,"question":60,"source":30,"type":31},[],353681042,[56,57,58,59],"11×11, 5×5, 3×3","11×11, 3×3, 5×5","3×3, 5×5, 11×11","5×5, 11×11, 3×3","AlexNet中卷积核大小递减的顺序是什么",{"answer":62,"createTime":5,"id":63,"options":64,"question":69,"source":30,"type":31},[],353681043,[65,66,67,68],"3次","1次","2次","4次","LeNet-5网络结构中,卷积层和池化层的组合出现了几次",{"answer":71,"createTime":5,"id":72,"options":73,"question":78,"source":30,"type":31},[],353681044,[74,75,76,77],"在深层网络中表现更差","更容易导致梯度消失","提高了网络的训练速率","计算更复杂","AlexNet中引入的ReLU激活函数相较于Sigmoid的优势是什么",{"answer":80,"createTime":5,"id":81,"options":82,"question":87,"source":30,"type":31},[],353681045,[83,84,85,86],"池化层","全连接层","卷积层","输出层","LeNet-5的哪一层负责最终的分类输出",{"answer":89,"createTime":5,"id":90,"options":91,"question":96,"source":30,"type":31},[],353681046,[92,93,94,95],"作者发现LRN对性能没有显著提升","因为LRN会增加计算复杂度","VGGNet的结构设计使得LRN无法应用","LRN与ReLU激活函数不兼容","VGGNet为何没有在卷积层之间使用局部响应归一化(LRN)",{"answer":98,"createTime":5,"id":99,"options":100,"question":105,"source":30,"type":31},[],353681047,[101,102,103,104],"可以增加模型的复杂度","能够减少过拟合的风险","提高模型对噪声的鲁棒性","有助于模型快速收敛","VGGNet中使用的ReLU激活函数有哪些优点"]