[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fjxa9QudfDh-moGKgO4vOQKy2Is2Ji2OzFG1gsXRnntI":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":16,"related":17,"source":27,"type":28},[],"2025-12-21 20:29:14",278112933,[8,9,10,11],"图像生成","图像分类","风格迁移","目标检测",{"courseId":13,"courseImg":14,"courseName":15},"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","在自动驾驶汽车中,用于感知周围环境、构建3D地图的最关键的计算机视觉任务是",[18,29,32,41,50,59,68,77,86,95],{"answer":19,"createTime":5,"id":20,"options":21,"question":26,"source":27,"type":28},[],278112932,[22,23,24,25],"图像的压缩与解压过程","从噪声到清晰图像的反向去噪过程","从清晰图像到噪声的前向扩散过程","图像的分类与标注过程","扩散模型生成图像的核心原理是学习哪个过程","v1",0,{"answer":30,"createTime":5,"id":6,"options":31,"question":16,"source":27,"type":28},[],[8,9,10,11],{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":27,"type":28},[],278112934,[36,37,38,39],"生成器-判别器","编码器-解码器","仅解码器","仅编码器","BERT模型采用的是哪种架构,使其特别擅长需要深度语义理解的任务",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":27,"type":28},[],278112935,[45,46,47,48],"CMU Sphinx","HTK","Kaldi","ESPnet","开源的HMM工具包(剑桥开发)是",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":27,"type":28},[],278112936,[54,55,56,57],"车辆的售价不透明","汽车车窗的透明度不够","系统的源代码没有公开","难以理解AI做出特定决策的具体原因和过程","当自动驾驶系统出现失误时,其复杂性和不透明性加大了责任归属的难度,这里的"不透明性"指的是什么",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":27,"type":28},[],278112937,[63,64,65,66],"卷积层","输出层","输入层","隐藏层","Softmax层通常用在分类任务的哪一层",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":27,"type":28},[],278112938,[72,73,74,75],"特征","数据量","样本","目标标签","在监督学习中,数据集的哪个部分是无监督学习所没有的",{"answer":78,"createTime":5,"id":79,"options":80,"question":85,"source":27,"type":28},[],278112939,[81,82,83,84],"计算依存关系","进行命名实体识别","去除停用词与无用符号","强制句法分析","生成词云前的"文本"通常会",{"answer":87,"createTime":5,"id":88,"options":89,"question":94,"source":27,"type":28},[],278112940,[90,91,92,93],"训练深度学习模型","停用词去除","词干提取\u002F词形还原","大小写统一","文本标准化通常不包含",{"answer":96,"createTime":5,"id":97,"options":98,"question":103,"source":27,"type":28},[],278112941,[99,100,101,102],"One-hot","Min-Max归一化","TF-IDF","标准差缩放","作为特征加权的经典方法是"]