[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"$fnDO8gZhid2lo-jkoG8ku-nC1LugXQCZGdEC9ilq6N4I":3},{"answer":4,"createTime":5,"id":6,"options":7,"origin":10,"question":13,"related":14,"source":24,"type":31},[],"2026-05-01 08:28:21",1096951136,[8,9],"对","错",{"courseImg":11,"courseName":12},"https:\u002F\u002Ftihai-oss-cloud.itihey.com\u002Fimg\u002Ff4e4dd841924a91dc656054650011ffd.jpeg","人工智能基础导学","一个已知为真的事实集,其内部不包含矛盾",[15,26,32,41,50,59,68,73,82,91],{"answer":16,"createTime":5,"id":17,"options":18,"question":23,"source":24,"type":25},[],1096950971,[19,20,21,22],"对部分数据引入监督","方法丰富、研究充分、性能好、成本高","方法简单、数据成本低、性能难以提升","以上都不是","描述弱监督的是","v2",0,{"answer":27,"createTime":5,"id":28,"options":29,"question":30,"source":24,"type":31},[],1096950986,[8,9],""自然语言处理"、"语言信息处理"、"计算语言学"三者之间无交叉关联",3,{"answer":33,"createTime":5,"id":34,"options":35,"question":40,"source":24,"type":25},[],1096951001,[36,37,38,39],"启发函数可以衡量两个状态孰优孰劣","启发式函数是主观上的评价,并在不同任务上有不同表示方法","启发式函数只有一种量化方法","大多数启发式搜索都有启发函数","关于启发式搜索的说法正确的是",{"answer":42,"createTime":5,"id":43,"options":44,"question":49,"source":24,"type":25},[],1096951046,[45,46,47,48],"具有多个输入端,每个输入端具相同的权重","神经元具有Sigmoid或者类似的可导激活函数","神经元能够根据误差信号,通过梯度下降法调整权重,实现学习","具有一个或多个输出端,输出端上的信号一致","标准神经元模型,不包括什么特点",{"answer":51,"createTime":5,"id":52,"options":53,"question":58,"source":24,"type":25},[],1096951054,[54,55,56,57],"OWL在工程实现上接近完美,但在逻辑上却过于复杂","语义web相继衍生出了"RDF资源描述框架"和"OWL网络本体语言"等新的框架","从linkded data开始,语义web开始进入"弱语义"的阶段","知识图谱包括知识抽取、知识表示、知识融合、知识推理等技术","下列说法错误的是()",{"answer":60,"createTime":5,"id":61,"options":62,"question":67,"source":24,"type":25},[],1096951065,[63,64,65,66],"Horn子句中的无头子句,用来表示事实:a_1←;a_2←","可以按照从左到右的顺序以及归结","只包含一个代表结论的正文字","Horn子句中的规则子句,用来表示推理规则:a←b_1∩b_2∩b_3∩…∩b_n","以下关于Horn子句的说法不正确的是( )",{"answer":69,"createTime":5,"id":70,"options":71,"question":72,"source":24,"type":31},[],1096951071,[8,9],"演绎更适合人类推理",{"answer":74,"createTime":5,"id":75,"options":76,"question":81,"source":24,"type":25},[],1096951092,[77,78,79,80],"BP算法的提出很好地解决了"多层"问题","2001年互联网泡沫破裂导致许多人工神经网络的研究被迫中断","LeCun将BP算法应用于神经网络的训练,并提出了卷积神经网络的第一个正式模型——LeNet-5","九十年代中期提出的SVM算法取代神经网络算法成为主流","下列关于人工神经网络发展历程不正确的是()",{"answer":83,"createTime":5,"id":84,"options":85,"question":90,"source":24,"type":25},[],1096951132,[86,87,88,89],"实体识别与链接","利用符号的方法","基于机器学习的推理","基于符号的推理","不属于知识图谱推理技术的是( )",{"answer":92,"createTime":5,"id":6,"options":93,"question":13,"source":24,"type":31},[],[8,9]]