[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$f8NehXXhI_1xrp9k1JFoB_jaPl5fpWjh2bLPXOJUJlgc":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":12,"question":19,"related":20,"source":30,"type":31},[],"2025-11-28 14:52:11",244303145,[8,9,10,11],"要让计算机理解图像,一定先要恢复物体的三维结构","深度学习仍需要专家提供知识,再通过神经网络堆叠结构,实现特征表征","特征匹配中常见的特征包括颜色特征、纹理特征、形状轮廓特征","马尔理论是一个自上而下的理论",{"count":13,"courseId":14,"courseImg":15,"courseName":16,"workId":17,"workName":18},85,"53e1d2ef4961cca8eea3e23969ad2cb9","https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002F03a579384a6dc297c89809b582fcc767.png","默认课程","exam_167157185","人工智能导论","下列关于计算机视觉研究的说法正确的是()",[21,32,41,50,59,68,77,86,95,104],{"answer":22,"createTime":5,"id":23,"options":24,"question":29,"source":30,"type":31},[],244303117,[25,26,27,28],"条目性的,规则性的知识","固定的概念、对象和事件","通过概念及其语义关系来表达的知识","存在从属关系的知识","下列不适合用框架法表示的知识是()","v1",0,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":30,"type":31},[],244303118,[36,37,38,39],"知识库","一阶谓词表示的知识","事实集","产生式表示的知识","所谓推理,就是从初始证据出发,按照某种策略,不断运用知识库中已有的知识,逐步匹配,直到推出结论的过程.这里的"初始证据"指的是()",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":30,"type":31},[],244303119,[45,46,47,48],"理性主义,符号主义","连接主义,经验主义","符号主义,连接主义","经验主义,行为主义","从人工智能研究流派来看,西蒙和艾伦纽维尔提出的"逻辑理论家"方法,应当属于()",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":30,"type":31},[],244303120,[54,55,56,57],"繁殖过程中为确保信息传递的准确性,要保证不会出现基因突变的情况","交叉基因的概率是遗传算法中的"交叉算子"","遗传算法中,通过"繁殖"实现了状态转移的过程","遗传算法中染色体断裂点不能固定在整个基因链正中间","以下关于遗传算法中"繁殖"的说法,错误的是()",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":30,"type":31},[],244303121,[63,64,65,66],"不确定性推理与确定性推理的不同点在于推理过程中每个环节都是不确定的","事实证据的可信度取值范围为[0,1]","不确定性推理基于产生式表示,确定性推理基于一阶谓词表示","推理规则的可信度取值范围为[0,1],表示前提与结论之间的推理强度","以下说法中正确的是()",{"answer":69,"createTime":5,"id":70,"options":71,"question":76,"source":30,"type":31},[],244303122,[72,73,74,75],"不对状态优劣进行判断,仅按照固定方式搜索","一个角色可以完成博弈搜索","对于许多棋类问题,需要两个甚至多个人参与,可以使用博弈算法","每个角色在做出决策时,不仅要考虑到自己的立场,还要预测对手可能的反应","对于博弈搜索,下列说法错误的是()",{"answer":78,"createTime":5,"id":79,"options":80,"question":85,"source":30,"type":31},[],244303123,[81,82,83,84],"行为主义","符号主义","经验主义","连接主义","早期的人工智能研究,主要采用()",{"answer":87,"createTime":5,"id":88,"options":89,"question":94,"source":30,"type":31},[],244303124,[90,91,92,93],"聚类算法","有监督学习","自动编码器","无监督学习","更接近人类学习的过程是()",{"answer":96,"createTime":5,"id":97,"options":98,"question":103,"source":30,"type":31},[],244303125,[99,100,101,102],"借用了深度学习的超强表示能力、蒙特拉洛树的概率优化能力","不属于博弈","AlphaGo在实现中也使用了大量人工设定的围棋知识","本质上解决问题的思路与A*搜索是类似的","关于AlphaGo说法错误的是()",{"answer":105,"createTime":5,"id":106,"options":107,"question":112,"source":30,"type":31},[],244303126,[108,109,110,111],"强化学习的概念是从Alphago战胜李世石之后才提出的","强化学习属于无监督学习的一种,不需要有监督信息","强化学习和有监督学习的过程相似,是"开环"的过程","在强化学习中,计算机通过不断与环境交互并通过环境反馈来逐渐适应环境","下列关于强化学习的说法正确的是()"]