[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fsX37E33v2MTBJXam7uTXaK0Deo80j73c_jjszCWo6xs":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":113},[],"2025-11-24 10:05:46",240594513,[8,9,10,11],"预测明天是否下雨","判断邮件是否为垃圾邮件","预测股票涨跌幅","预测图片中是猫还是狗",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},72,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","exam_167092916","动手学AI:人工智能通识与实践","以下哪些任务属于分类任务",[21,32,41,50,59,68,77,86,95,104],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],240594430,[25,26,27,28],"时间","类别","有序","数值","视觉通道"饱和度"适用于哪类数据","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],240594432,[36,37,38,39],"8","14","12","10","二分查找在1~1000范围内最多需要几次必中",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],240594433,[45,46,47,48],"可证伪性","迭代性","准确性","通用性","计算的两个基本性质是组合性和",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],240594435,[54,55,56,57],"完整复制外部世界的所有细节","提高计算速度和存储容量","增加神经网络的层数","通过简化表征来辅助信息处理和预测","图灵奖得主杨立昆提出的"内在世界模型"的核心思路是?( )",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],240594437,[63,64,65,66],"密度聚类","图聚类","原型聚类","层次聚类","K均值聚类属于哪种聚类方法",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":30,"type":31},[],240594439,[72,73,74,75],"温度参数不影响事实性问题的回答","设置较高温度,让AI有更多创造性","设置较低温度,确保输出准确和保守","随机设置温度,以获得多样化答案","温度参数会影响AI文本生成的特性.当需要AI回答"浙江的省会是哪里"这类事实性问题时,应该如何设置温度参数?( )",{"answer":78,"createTime":5,"id":79,"options":80,"question":85,"source":30,"type":31},[],240594441,[81,82,83,84],"循环神经网络(RNN)","卷积神经网络(CNN)","n-gram统计模型","Transformer架构及其自注意力机制","2017年提出的哪项技术架构成为语言模型发展的真正分水岭?( )",{"answer":87,"createTime":5,"id":88,"options":89,"question":94,"source":30,"type":31},[],240594443,[90,91,92,93],"检索信息→用户提问→生成答案→提取上下文","提取上下文→检索信息→用户提问→生成答案","用户提问→检索信息→提取上下文→生成答案","生成答案→检索信息→提取上下文→返回结果","RAG系统的工作流程是?( )",{"answer":96,"createTime":5,"id":97,"options":98,"question":103,"source":30,"type":31},[],240594445,[99,100,101,102],"完全依赖外部数据库,模型本身不需要知识","让模型记住所有知识,成为百科全书","不断重新训练模型,保持知识更新","不是让模型记住所有知识,而是教会它查找和使用知识","根据课程内容,RAG(Retrieval Augmented Generation)的核心思想是什么?( )",{"answer":105,"createTime":5,"id":106,"options":107,"question":112,"source":30,"type":31},[],240594446,[108,109,110,111],"仅能处理单一模态的输入数据","先将图片转成特征并视作文本,交给语言模型生成回答","无需依赖编码器将多模态数据转成特征向量","把文字当作生成指令,直接参与图像生成过程","多模态生成的 "理解型(语言为主型)" 路线的核心特点是?( )",1]