Quizzes for Chapter 1
1单选(1分)图灵测试旨在给予哪一种令人满意的操作定义得分/总分
正确答案：A、B你选对了
5多选(1分)选择下列计算机系统中属于人工智能的实例得分/总分
?
A.人类思考
A.Web搜索引擎 B.超市条形码扫描器
C.声控电话菜单该题无法得分/1.00 D.智能个人助理该题无法得分/1.00
正确答案：A、D你错选为C、D
? ? ? ?
?
B.人工智能
?
C.机器智能1.00/1.00
?
D.机器动作
正确答案：C你选对了
2多选(1分)选择以下关于人工智能概念的正确表述得分/总分
? A.人工智能旨在创造智能机器该题无法得分/1.00 ?
B.人工智能是研究和构建在给定环境下表现良好的
智能体程序该题无法得分/1.00
?
C.人工智能将其定义为人类智能体的研究该题无法
得分/1.00
? D.人工智能是为了开发一类计算机使之能够完成通
常由人类所能做的事该题无法得分/1.00 正确答案：A、B、D你错选为A、B、C、D
3多选(1分)如下学科哪些是人工智能的基础？得分/总分
? A.经济学0.25/1.00 ? B.哲学0.25/1.00 ? C.心理学0.25/1.00 ?
D.数学0.25/1.00
正确答案：A、B、C、D你选对了
4多选(1分)下列陈述中哪些是描述强AI(通用AI)的正确答案？得分/总分
? A.指的是一种机器，具有将智能应用于任何问题的
能力0.50/1.00
? B.是经过适当编程的具有正确输入和输出的计算
机，因此有与人类同样判断力的头脑0.50/1.00
? C.指的是一种机器，仅针对一个具体问题 ?
D.其定义为无知觉的计算机智能，或专注于一个狭
窄任务的AI
6多选(1分)选择下列哪些是人工智能的研究领域 得分/总分
? A.人脸识别0.33/1.00 ? B.专家系统0.33/1.00 ? C.图像理解 ?
D.分布式计算
正确答案：A、B、C你错选为A、B
7多选(1分)考察人工智能(AI)的一些应用，去发现目前下列哪些任务可以通过AI来解决得分/总分
? A.以竞技水平玩德州扑克游戏0.33/1.00 ? B.打一场像样的乒乓球比赛
? C.在Web上购买一周的食品杂货0.33/1.00 ?
D.在市场上购买一周的食品杂货
正确答案：A、B、C你错选为A、C
8填空(1分)理性指的是一个系统的属性，即在_________的环境下做正确的事。得分/总分 正确答案：已知
1单选(1分)图灵测试旨在给予哪一种令人满意的操作定义得分/
总分
? A.人类思考 ? B.人工智能
? C.机器智能1.00/1.00 ?
D.机器动作
正确答案：C你选对了
2多选(1分)选择以下关于人工智能概念的正确表述得分/总分
? ?
A.人工智能旨在创造智能机器该题无法得分/1.00 B.人工智能是研究和构建在给定环境下表现良好的
智能体程序该题无法得分/1.00
? ? ?
B.专家系统0.33/1.00 C.图像理解 D.分布式计算
正确答案：A、B、C你错选为A、B
7多选(1分)考察人工智能(AI)的一些应用，去发现目前下列哪些
?
得分/1.00
C.人工智能将其定义为人类智能体的研究该题无法
? D.人工智能是为了开发一类计算机使之能够完成通
任务可以通过AI来解决得分/总分
常由人类所能做的事该题无法得分/1.00 正确答案：A、B、D你错选为A、B、C、D
3多选(1分)如下学科哪些是人工智能的基础？得分/总分
? A.经济学0.25/1.00 ? B.哲学0.25/1.00 ? C.心理学0.25/1.00 ?
D.数学0.25/1.00
正确答案：A、B、C、D你选对了
4多选(1分)下列陈述中哪些是描述强AI(通用AI)的正确答案？ 得分/总分
? A.指的是一种机器，具有将智能应用于任何问题的
能力0.50/1.00
? B.是经过适当编程的具有正确输入和输出的计算
机，因此有与人类同样判断力的头脑0.50/1.00
? C.指的是一种机器，仅针对一个具体问题 ?
D.其定义为无知觉的计算机智能，或专注于一个狭
窄任务的AI
正确答案：A、B你选对了
5多选(1分)选择下列计算机系统中属于人工智能的实例得分/总分
? A.Web搜索引擎 ? B.超市条形码扫描器
? C.声控电话菜单该题无法得分/1.00
?
D.智能个人助理该题无法得分/1.00
正确答案：A、D你错选为C、D
6多选(1分)选择下列哪些是人工智能的研究领域得分/总分
? A.人脸识别0.33/1.00
? A.以竞技水平玩德州扑克游戏0.33/1.00 ? B.打一场像样的乒乓球比赛
? C.在Web上购买一周的食品杂货0.33/1.00 ?
D.在市场上购买一周的食品杂货
正确答案：A、B、C你错选为A、C
8填空(1分)理性指的是一个系统的属性，即在_________的环境下做正确的事。得分/总分 正确答案：已知 Quizzes for Chapter 2
1多选(1分)对于如下比拟，选择哪些方法更通用并且更适合于科学开发得分/总分
? A.理性动作
? B.类人动作该题无法得分/1.00 ? C.理性思考该题无法得分/1.00 ?
D.类人思考
正确答案：A、C你错选为B、C
2多选(1分)理性智能体指的是有正确行为的智能体，但正确的行
为意味着什么？考虑智能体行为的后果，选择下列有关“正确的行为”概念的真实陈述得分/总分
?
A.如果该序列是所期望的，则该智能体表现良好
0.33/1.00
?
B.智能体在某个环境中依据感知生成动作序列 ?
C.但若该序列是不期望的，则该智能体对其环境造
成破坏
? D.这些动作序列引起环境改变而产生状态序列
0.33/1.00
正确答案：A、B、D你错选为A、D
3多选(1分)PEAS是一种任务环境描述，它代表 得分/总分 8填空(1分)智能体可看作是通过_________感知外部环境，并且通过执行器作用于外部环境的任何事物。得分/总分 正确答案：感受器
1多选(1分)对于如下比拟，选择哪些方法更通用并且更适合于科学开发得分/总分
? ? ? ?
A.性能该题无法得分/1.00 B.动作器该题无法得分/1.00 C.感觉该题无法得分/1.00
?
D.感受器该题无法得分/1.00
A.类人动作该题无法得分/1.00 正确答案：A、B、D你错选为A、B、C、D
4多选(1分)下列中语句哪些与智能体环境类型有关得分/总分
? A.完全可观测与部分可观测0.25/1.00 ? B.单智能体与多智能体0.25/1.00 ? C.阵发性与连续性0.25/1.00 ?
D.确定性与随机性0.25/1.00
正确答案：A、B、C、D你选对了
5多选(1分)考虑智能体函数与智能体程序的差异，从下列陈述中选择正确的答案得分/总分
? A.一个智能体程序实现一个智能体函数
? B.智能体程序与智能体函数没有任何关系 ?
C.一个智能体函数实现一个智能体程序该题无法得
分/1.00
? D.智能体程序包含智能体函数该题无法得分/1.00
正确答案：A、D你错选为C、D
6多选(1分)选择下列哪些方法可以用于表示表示智能体的状态得分/总分
? A.结构式该题无法得分/1.00
? B.模块式该题无法得分/1.00
? C.网络式该题无法得分/1.00 ?
D.因子式该题无法得分/1.00
正确答案：A、D你错选为A、B、C、D
7填空(1分)凭借符号及他们之间的关系来表征信息的人工智能方法是____________，而用网络内部的一种分布式形式来表征信息的是联结主义AI。得分/总分 正确答案：符号主义AI
? B.理性动作 ? C.类人思考
?
D.理性思考该题无法得分/1.00
正确答案：B、D你错选为A、D
2多选(1分)理性智能体指的是有正确行为的智能体，但正确的行
为意味着什么？考虑智能体行为的后果，选择下列有关“正确的行为”概念的真实陈述得分/总分
? A.智能体在某个环境中依据感知生成动作序列 ?
B.但若该序列是不期望的，则该智能体对其环境造
成破坏
?
C.这些动作序列引起环境改变而产生状态序列
0.33/1.00
? D.如果该序列是所期望的，则该智能体表现良好
0.33/1.00
正确答案：A、C、D你错选为C、D
3多选(1分)PEAS是一种任务环境描述，它代表 分/总分
? A.感受器0.33/1.00 ?
B.动作
?
C.性能0.33/1.00 ?
D.动作器0.33/1.00
正确答案：A、C、D你选对了
4多选(1分)下列中语句哪些与智能体环境类型有关得分/总分
? A.完全可观测与部分可观测该题无法得分/1.00 ? B.单智能体与多智能体该题无法得分/1.00 ? C.好的智能体与差的智能体该题无法得分/1.00 ?
D.确定性与随机性该题无法得分/1.00
正确答案：A、B、D你错选为A、B、C、D
?
5多选(1分)考虑智能体函数与智能体程序的差异，从下列陈述中选择正确的答案得分/总分
B.f(n) = g(n) C.f(n) = g(n) - h(n) D.f(n) = h(n)1.00/1.00
正确答案：D你选对了
3单选(1分)设h(n)表示启发式函数且g(n)表示代价，则A*搜索所
? ?
? ? ? ?
A.智能体程序与智能体函数没有任何关系 B.一个智能体函数实现一个智能体程序
C.一个智能体程序实现一个智能体函数0.50/1.00 D.智能体程序包含智能体函数0.50/1.00
使用的评价函数是:得分/总分
? A.f(n) = g(n) + h(n)1.00/1.00 正确答案：C、D你选对了
6多选(1分)选择下列哪些方法可以用于表示表示智能体的状态 得分/总分
? A.结构式0.50/1.00
? B.模块式 ? C.网络式
?
D.原子式
正确答案：A、D你错选为A
7填空(1分)凭借符号及他们之间的关系来表征信息的人工智能方法是____________，而用网络内部的一种分布式形式来表征信息的是联结主义AI。得分/总分 正确答案：符号主义AI
8填空(1分)智能体可看作是通过_________感知外部环境，并且通过执行器作用于外部环境的任何事物。得分/总分 正确答案：感受器 Quizzes for Chapter 3
1单选(1分)有两种8皇后问题的形式化方式。“初始时8个皇后都放在棋盘上，然后再进行移动”是哪一种形式化方式？得分/总分
? A.半态形式化
? B.增量形式化0.00/1.00 ? C.正则形式化
?
D.全态形式化
正确答案：D你错选为B
2单选(1分)设h(n)表示启发式函数且g(n)表示代价，则贪婪搜索所使用的评价函数是得分/总分
? A.f(n) = g(n) + h(n)
?
B.f(n) = h(n) ?
C.f(n) = g(n) - h(n) ?
D.f(n) = g(n)
正确答案：A你选对了
4多选(1分)下列哪些项用于对问题进行形式化得分/总分
?
A.感知
? B.初始状态该题无法得分/1.00 ? C.动作该题无法得分/1.00 ?
D.环境该题无法得分/1.00
正确答案：B、C你错选为B、C、D
5多选(1分)选择如下哪些搜索方法属于无信息搜索得分/总分
? A.贪婪搜索 ?
B. A*搜索
? C.双向搜索0.50/1.00 ?
D.宽度优先搜索0.50/1.00
正确答案：C、D你选对了
6多选(1分)除了问题本身的定义之外，使用问题特定知识的搜索策略被认为是得分/总分
?
A. 启发式搜索0.50/1.00 ? B.有信息搜索0.50/1.00 ? C.二元搜索 ?
D.无信息搜索
正确答案：A、B你选对了
7填空(1分)某些_______或NP难问题只能通过搜索来求解。得分/总分
正确答案：NP完
8填空(1分)问题形式化是给定一个目标，决定要考虑的_______与状态的处理。得分/总分 正确答案：动作
1单选(1分)有两种8皇后问题的形式化方式。“初始时8个皇后都放在棋盘上，然后再进行移动”是哪一种形式化方式？得分/总分
? D.智能体函数
正确答案：A、B、C你错选为A、C
5多选(1分)选择如下哪些搜索方法属于无信息搜索得分/总分
? ? ? ?
A. A*搜索
B.深度优先搜索0.33/1.00 C. 一致代价搜索0.33/1.00 D.深度受限搜索
? A.正则形式化
? B.全态形式化1.00/1.00 ? C.半态形式化
?
D.增量形式化
正确答案：B你选对了
2单选(1分)设h(n)表示启发式函数且g(n)表示代价，则贪婪搜索所使用的评价函数是得分/总分
? A.f(n) = g(n)
? B.f(n) = h(n)1.00/1.00 ? C.f(n) = g(n) - h(n) ?
D.f(n) = g(n) + h(n)
正确答案：B你选对了
3单选(1分)设h(n)表示启发式函数且g(n)表示代价，则A*搜索所使用的评价函数是:得分/总分
? A.f(n) = h(n) ? B.f(n) = g(n)
? C.f(n) = g(n) + h(n)1.00/1.00 ?
D.f(n) = g(n) - h(n)
正确答案：C你选对了
4多选(1分)下列哪些项用于对问题进行形式化得分/总分
? A.初始状态0.33/1.00 ? B.路径检测
?
C.目标检测0.33/1.00
正确答案：B、C、D你错选为B、C
6多选(1分)除了问题本身的定义之外，使用问题特定知识的搜索策略被认为是得分/总分
?
A.有信息搜索0.50/1.00 ? B.二元搜索 ? C.无信息搜索
?
D. 启发式搜索0.50/1.00
正确答案：A、D你选对了
7填空(1分)某些_______或NP难问题只能通过搜索来求解。得分/总分
正确答案：NP完
8填空(1分)问题形式化是给定一个目标，决定要考虑的_______与状态的处理。得分/总分 正确答案：动作 Quizzes for Chapter 4
1单选(1分)Keeping just one node in memory might seem to be an extreme reaction to the problem of memory limitations. Local beam search keeps track of:在内存中仅保存一个节点似乎是对
内存限制问题的极端反应。局部束搜索保持：得分/总分
?
A.m states rather than n states.m个状态而不是n
个
?
B.just m states rather than n states仅有n状态而
不是m
? C.k states rather than just one.k个状态而不仅仅
为一1.00/1.00
?
D.just one rather than k states.仅有一个状态而不
是k个
2单选(1分)A genetic algorithm is a variant of stochastic beam search, in which successor states are generated:遗传算法是随机束搜索的一个变体，其中后继节点的生成是由：得分/总分
? C.The inner loop of the simulated annealing
algorithm is quite similar to hill climbing.模拟退火算法的内循环与爬山法非常相似。0.50/1.00
? A.by combining two parent nodes rather than by
modifying a single node.组合单一状态而不是组合两个双亲状态。
? D.Instead of picking the best move, simulated
annealing algorithm picks a random move.模拟退火算法不是选择最佳行动，而是选择随机行动。0.50/1.00
5填空(1分)Ant Colony Optimization (ACO) algorithm was inspired by the behavior of ants seeking a path between
? B.by combining two parent states rather than by
modifying a single state.组合两个双亲状态而不是修改单一状态。1.00/1.00
? C.by modifying a single node rather than by
_______ and a source of food.蚁群优化算法是受蚂蚁在combining two parent nodes.组合单一节点而不是组合两个双亲节点。
? D.by modifying a single state rather than by
combining two parent states.组合两个双亲节点而不是修改单一节点。
3多选(1分)Hill climbing search is sometimes called greedy local search because it grabs a good neighbor state without thinking ahead about where to go next. Unfortunately, it often gets stuck for the three reasons:爬山搜索有时也被称为贪婪局部搜索，因为它只顾抓住一个好的邻接点的状态，而不提前思考下一步该去哪儿。它在三种情况下经常被困：得分/总分
? A. Ridges山岭0.33/1.00 ? B.Mountain高山
? C.Plateaux高原0.33/1.00
?
D.Local maxima局部最大值0.33/1.00
4多选(1分)Which of the following statements are true about Simulated annealing algorithm？以下关于模拟退火算法的陈述哪些是正确的？得分/总分
? A.Instead of picking the random move, simulated
annealing algorithm picks a best move.模拟退火算法不是选择随机行动，而是选择最佳行动。
? B.The inner loop of the simulated annealing
algorithm is very different from hill climbing.模拟退火算法的内循环与爬山法完全不同。
_______和食物源之间寻找路径行为的启发而形成的。 蚁巢 1.00/1.00
6填空(1分)Inspired by social behavior of birds and fishes,
Particle Swarm Optimization (PSO) algorithm uses a number of ________ that constitute a swarm moving around in the search space looking for the best solution.受鸟类和鱼类的社会行为的启发，粒子群优化算法采用若干_______构成一个围绕搜索空间移动的群体来寻找最优解。 粒子 1.00/1.00
7填空(1分)Local search algorithms operate using a single ______ (rather than multiple paths) and generally move only to neighbors of that node.局部搜索算法使用一个______（而不是多条路径），并且通常仅移动到该节点相邻的节点。
当前节点 1.00/1.00
8填空(1分)In addition to finding goals, local search algorithms are useful for solving pure _________, in which the aim is to find the best state according to an objective function.除了寻找目标之外，局部搜索算法对解决纯_________也很有效。其目的是根据一个目标函数找到其最好的状态。 优化问题 1.00/1.00 Quizzes for Chapter 5
1单选(1分)Which of the following is a true statement about games?以下关于博弈的陈述哪个是正确的？得分/总分
?
A.Local search problems are often known as
games.局部搜索问题通常称为博弈
? B.Heuristic search problems are often known as
games.启发式搜索问题通常称为博弈
? C.Classical search problems are often known as
games.经典搜索问题通常称为博弈
? D.Adversarial search problems are often known
as games.对抗搜索通常称为博弈1.00/1.00
2单选(1分)___________ describes a situation in which the interacting agents' aggregate gains and losses can be less than or more than zero.___________中智能体交互动作的总收益和损失可以小于或大于零得分/总分
? C.Alpha–beta pruning is to increase the number
of nodes that are evaluated by the minimax algorithm in its search tree.Alpha–beta剪枝旨在增加其搜索树中由minimax算法评价的节点数量。
? D.Alpha–beta pruning is to decrease the number
of nodes that are evaluated by the minimax algorithm in its search tree.Alpha–beta剪枝旨在减少其搜索树中由minimax算法评价的节点数量。0.50/1.00
? ? A.Zero sum game零和博弈 B. Computer game计算机博弈 ? C.Two-player game双人博弈
?
D.Non-zero sum game非零和博弈1.00/1.00
3多选(1分)Select the following true statements regarding the concept of minimax rule for a zero sum game.从如下关于零和博弈maximum概念中选择正确的答案。得分/总分
? A.Each player maximizes the maximum payoff
possible for itself.每个玩家会使自己可能的最大收益变得最大。0.50/1.00
? B.Each player maximizes the maximum loss
possible for the other.每个玩家会使对手可能的最大损失变得最大。0.50/1.00
? C.Each player minimizes the maximum payoff
possible for itself.每个玩家会使自己可能的最大收益变得最小。
? D.Each player minimizes the maximum loss
possible for the other.每个玩家会使对手可能的最大损失变得最小。
4多选(1分)Which of the following statements are true about alpha-beta pruning?以下关于alpha–beta剪枝的陈述哪些是正确的？得分/总分
? A.Alpha–beta pruning is to add large parts that
are evaluated by the minimax algorithm in its search
tree.Alpha–beta剪枝旨在添加其搜索树中由minimax算法评价的大部分。
? B.Alpha–beta pruning is to eliminate large parts
that are evaluated by the minimax algorithm in its search tree.Alpha–beta剪枝旨在消除其搜索树中由minimax算法评价的大部分。0.50/1.00
5填空(1分)Claude Shannon proposed instead that programs should cut off the search earlier and apply a _______________ to states in the search, effectively turning nonterminal nodes into terminal leaves.克劳德·香农提出：程序应该早一些剪断搜索，并在搜索中对状态应用________________，有效地将非终端节点转换为终端叶节点。（请填写中文答案） 启发式评估函数 0.00/1.00
6填空(1分)____________ is a dynamic game with probabilistic
transitions played by one or more players.____________是一种具有概率转换的动态博弈，有一个或多个玩家。（请填写中文答案）
随机博弈 1.00/1.00
7填空(1分)Monte-Carlo methods are a broad class of computational algorithms that rely on ________________ to obtain numerical results.蒙特卡罗方法是一大类计算算法，它凭
借________________来获得数值结果。（请填写中文答案） 重复随机采样 1.00/1.00
8填空(1分)___________ tree search is on the analysis of the most promising moves, expanding the search tree based on
random sampling of the search space.___________树搜索对最有利的动作进行分析，根据搜索空间的随机采样来扩展搜索树。（请填写中文答案） 蒙特卡罗 1.00/1.00 Quizzes for Chapter 6
1单选(1分)Select the following true one that is used to the state representation for constraint satisfaction problems (CSPs).从如
下用于约束满足问题 (CSP)的状态表示中选择正确的答案。得分/总分
? A.atomic原子0.00/1.00 ? B.Molecular分子 ?
C.Structure结构
? D.Factored因子
2单选(1分)Assume that {A, B, C, D} are variables, the domain of each variable is {u, v, w}, and != denotes \which of the following expressions is a binary constraint on CSP formalism?{A, B, C, D}为变量，每个变量的域是{u, v, w}，且“!=”表示不等于，从如下表达式中选择那个是CSP形式化的2元约束？得分/总分
5多选(1分)Select the following true statements regarding the concept of \从如下有关“回溯搜索”概念中选择正确的答案。得分/总分
? A.It incrementally builds candidates to the
solutions, and abandons each partial candidate c, as soon as it determines that c cannot possibly be completed to a valid solution.每次为变量选择值并且当变量有一个或多个合法赋值时回溯。
? A.Alldiff(A, B, C, D)
? B.<(A), A = v>0.00/1.00 ? C.Diff(A, D) ?
D.A + B = C
3多选(1分)Compare CSP and state-space search, and select correct statements from following ones. 比较CSP和状态空间搜索，并从下列叙述中选择正确的答案。得分/总分
? A.CSP solving system can be slower than
state-space search solving system.CSP求解系统会比状态空间搜索求解系统慢。
? B.CSP solving system can be faster than
state-space search solving system.CSP求解系统会比状态空间搜索求解系统快。0.50/1.00
? C.State-space search can quickly eliminate large
swatches of the search space.状态空间搜索可以快速排除大的搜索空间样本。
? D.CSP can quickly eliminate large swatches of
the search space.CSP可以快速排除大的搜索空间样本。0.50/1.00
4多选(1分)Which of the following statements are true types of types of local consistency for constraint propagation?如下陈述中哪些是约束传播局部一致性的正确类型？得分/总分
? A.Path consistency路径一致该题无法得分/1.00 ? B.Loop consistency环路一致
? C.Tree consistency树一致该题无法得分/1.00
?
D.Node consistency节点一致该题无法得分/1.00
?
B.It incrementally builds candidates to the
solutions, and abandons each partial candidate c, as soon as it determines that c cannot possibly be completed to an invalid solution. 递增地构建解的候选，并且一旦确定部分候选c不能成为合法的解，就将c抛弃。0.50/1.00
? C.It chooses values for one variable at a time and
backtracks when a variable has no legal values left to assign.每次为变量选择值并且当变量没有合法赋值时回溯。0.50/1.00
? D.It chooses values for one variable at a time and
backtracks when a variable has one more legal value left to assign.递增地构建解的候选，并且一旦确定部分候选c不能成为非法的解，就将c抛弃。
1单选(1分)Select the following true one that is used to the state
representation for constraint satisfaction problems (CSPs).从如下用于约束满足问题 (CSP)的状态表示中选择正确的答案。
得分/总分
? A.Molecular分子 ?
B. Networked网络 ? C. atomic原子
?
D.Factored因子1.00/1.00
2单选(1分)Assume that {A, B, C, D} are variables, the domain of each variable is {u, v, w}, and != denotes \which of the following expressions is a binary constraint on CSP formalism?设{A, B, C, D}为变量，每个变量的域是{u, v, w}，且“!=”
表示不等于，从如下表达式中选择那个是CSP形式化的2元约束？得分/总分
?
A.Diff(A, D)1.00/1.00 ?
B.A + B = C
? ?
C.<(A), A = v> D.Alldiff(A, B, C, D)
3多选(1分)Compare CSP and state-space search, and select correct statements from following ones. 比较CSP和状态空间搜索，并从下列叙述中选择正确的答案。得分/总分
solution. 递增地构建解的候选，并且一旦确定部分候选c不能成为合法的解，就将c抛弃。0.50/1.00
? C.It incrementally builds candidates to the
solutions, and abandons each partial candidate c, as soon as it determines that c cannot possibly be completed to a valid solution.每次为变量选择值并且当变量有一个或多个合法赋值时回溯。
? A.CSP solving system can be faster than
state-space search solving system.CSP求解系统会比状态空间搜索求解系统快。0.50/1.00
? B.CSP can quickly eliminate large swatches of
the search space.CSP可以快速排除大的搜索空间样本。0.50/1.00
? C.State-space search can quickly eliminate large
swatches of the search space.状态空间搜索可以快速排除大的搜索空间样本。
? D.CSP solving system can be slower than
state-space search solving system.CSP求解系统会比状态空间搜索求解系统慢。
4多选(1分)Which of the following statements are true types of types of local consistency for constraint propagation?如下陈述中哪些是约束传播局部一致性的正确类型？得分/总分
? A.k-consistencyk一致0.33/1.00 ? B.Tree consistency树一致 ? C.Arc consistency弧一致0.33/1.00 ?
D.Node consistency节点一致0.33/1.00
5多选(1分)Select the following true statements regarding the concept of \从如下有关“回溯搜索”概念中选择正确的答案。得分/总分
? A.It chooses values for one variable at a time and
backtracks when a variable has no legal values left to assign.每次为变量选择值并且当变量没有合法赋值时回溯。0.50/1.00
? B.It incrementally builds candidates to the
solutions, and abandons each partial candidate c, as soon as it determines that c cannot possibly be completed to an invalid
? D.It chooses values for one variable at a time and
backtracks when a variable has one more legal value left to assign.递增地构建解的候选，并且一旦确定部分候选c不能成为非法的解，就将c抛弃。
6填空(1分)A constraint satisfaction problem (CSP) is defined as a set of objects whose state must satisfy a number of
_______________.约束满足问题 (CSP) 被定义为其状态必须满足若干_______________的一组对象。 约束和限制 1.00/1.00
7填空(1分)In choosing a new value for a variable, min-conflicts
heuristic is to select the value that results in the _________ with
other variables.在对一个变量选择一个新值时，最小冲突启发式选择导致与其它变量呈现__________的值。 最少冲突 1.00/1.00
8填空(1分)To reduce a constraint graph to a tree structure, two approaches can be used that are ___________and tree decomposition. 为了简化约束图为树结构，有两种方法可以采用，即___________和树分解。
割集调节 1.00/1.00 Quizzes for Chapter 7
1单选(1分)Which of the following has been defined with reference to information? 下列中哪一项是根据信息来定义的？得分/总分
? A.Data数据 ? B.Information信息
? C.Knowledge知识1.00/1.00 ?
D.Wisdom智慧
2单选(1分)What kind of knowledge will be used to describe how a problem is solved?哪种知识可用于描述问题如何求解？得分/总分
? A.Declarative knowledge陈述性知识
? ? ?
B. Procedural knowledge过程性知识1.00/1.00 C.Dynamic knowledge动态知识 D.Heuristic knowledge启发性知识
3单选(1分)Select which of the following approaches are true using first order logic.选择以下哪种方法可以使用一阶逻辑。得分/总分
? B.Ontologies cannot be divided the types of upper
ontology, domain ontology, or hyper ontology.无法将本体分为上层本体、领域本体、或混合本体。该题无法得分/1.00
? C. An ontology is a formal naming and definition
of the types, properties, and interrelationships of the entities for a particular domain of discourse.本体是一种对特定论域中实体的类型、特性和相互关系的形式化命名和定义。该题无法得分/1.00
? A.Declarative approaches陈述性方法1.00/1.00 ? D.An ontology provides a common vocabulary of
? B.Functional approaches函数型方法 ? C.Procedural approaches过程性方法 ?
D.Objective approaches对象型方法
4多选(1分)Select the following true statements regarding the concept of \选择如下关于“语义网络”概念的正确陈述。得分/总分
? A.It can be used when one has knowledge that is
best understood as a set of concepts that are related to one another.
语义网络可以用于当所具有的知识可被很好地理解为一组彼此相关的概念时。0.33/1.00
? B.It can represent large domains, performance or
meta-knowledge very well.可以很好地表示大的域、性能或元知识。
? C.It can represent the semantic relations between
concepts.可以表示概念之间的语义关系。
? D.It can be represented as a directed or
undirected graph, consisting of nodes used to represent concepts, and arcs to represent semantic relations between the concepts.可以被表示为一种直接或间接的图，由表示概念的节点和表示概念之间语义关系的弧组成。0.33/1.00
5多选(1分)Select which of the following statements are true about ontology.选择下列关于本体的陈述哪些是正确的。得分/总分
? A.Ontologies cannot be created to organize
information that will be applied to problem solving.无法创建本体来组织可用于问题求解的信息。
an area and define the meaning of the terms and the
relationships between them.本体提供一个领域的公共词汇，并且定义一些术语的含义和它们之间的关系。该题无法得分/1.00 6多选(1分)The synonyms of Bayesian networks include:贝叶斯网络的同义词包括：得分/总分
? A.Neural network神经网络
? B.Probabilistic network概率网络0.33/1.00 ? C. Belief network信念网络0.33/1.00 ?
D.Causal network因果网络0.33/1.00
1单选(1分)Which of the following has been defined with reference to information? 下列中哪一项是根据信息来定义的？得分/总分
? A.Wisdom智慧 ?
B.Data数据
? C.Knowledge知识1.00/1.00 ?
D.Information信息
2单选(1分)What kind of knowledge will be used to describe how a problem is solved?哪种知识可用于描述问题如何求解？得分/总分
? A.Heuristic knowledge启发性知识 ? B.Declarative knowledge陈述性知识 ?
C.Static knowledge静态知识
?
D.Procedural knowledge过程性知识1.00/1.00
3单选(1分)Select which of the following approaches are true using first order logic.选择以下哪种方法可以使用一阶逻辑。得分/总分
? C.Ontologies cannot be divided the types of upper
ontology, domain ontology, or hyper ontology.无法将本体分为上层本体、领域本体、或混合本体。
? ? ? ?
A.Procedural approaches过程性方法 B.Objective approaches对象型方法 C.Functional approaches函数型方法
D.Declarative approaches陈述性方法1.00/1.00
? D.Ontologies cannot be created to organize
information that will be applied to problem solving.无法创建本体来组织可用于问题求解的信息。
6多选(1分)The synonyms of Bayesian networks include:贝叶斯网络的同义词包括：得分/总分
4多选(1分)Select the following true statements regarding the concept of \选择如下关于“语义网络”概念的正确陈述。得分/总分
? A.It can represent the semantic relations between
concepts.可以表示概念之间的语义关系。0.33/1.00
? B.It can be represented as a directed or
undirected graph, consisting of nodes used to represent concepts, and arcs to represent semantic relations between the concepts.可以被表示为一种直接或间接的图，由表示概念的节点和表示概念之间语义关系的弧组成。0.33/1.00
? C.It can represent large domains, performance or
meta-knowledge very well.可以很好地表示大的域、性能或元知识。
? D.It can be used when one has knowledge that is
best understood as a set of concepts that are related to one another.语义网络可以用于当所具有的知识可被很好地理解为一组彼此相关的概念时。0.33/1.00
5多选(1分)Select which of the following statements are true about ontology.选择下列关于本体的陈述哪些是正确的。得分/总分
? A.An ontology is a formal naming and definition of
the types, properties, and interrelationships of the entities for a particular domain of discourse.本体是一种对特定论域中实体的类型、特性和相互关系的形式化命名和定义。0.50/1.00
? B.An ontology provides a common vocabulary of
an area and define the meaning of the terms and the
relationships between them.本体提供一个领域的公共词汇，并且定义一些术语的含义和它们之间的关系。0.50/1.00
? A.Belief network信念网络0.33/1.00 ? B.Social network社交网络
? C.Causal network因果网络0.33/1.00 ?
D.Probabilistic network概率网络0.33/1.00
7填空(1分)A ______________ system consists of a knowledge base and an inference engine, where knowledge base represents facts about the world, inference engine can reason about those facts.______________系统由知识库和搜索引擎组成，其中，知识库表示关于世界的事实，推理引擎则可以对这些事实进行推理。 知识库 1.00/1.00
8填空(1分)__________ representation focus on designing computer representations that capture knowledge about the
world that can be used to solve complex problems. __________表示关注于设计计算机表示来采集关于世界的知识，可用于解决复杂的问题。 知识 1.00/1.00 Quizzes for Chapter 8
1单选(1分)Learned the differences between single-agent problem and multi-agent problem, select a correct one form following descriptions.学习了单智能体问题和多智能体问题之间
的区别后，从如下描述中选择正确的答案。得分/总分
? A.Multi-effector problem is a single-agent problem,
but multi-body problem is not.多效用器是单智能体问题，而多躯体是多智能体问题。
?
B.Multi-body problem is a multi-agent problem,
but multi- effector problem is not.多躯体是单智能体问题，而多效用器是多智能体问题。
? C.Both of multi-effector problem and multi-body
problem is a single-agent problem.多效用器和多躯体这两者都是单智能体问题。1.00/1.00
5多选(1分)The characteristics of multi-agent are:多智能体的特征是：得分/总分
? ? ? ?
A.Autonomy自主性0.50/1.00 B.Decentralization分散化0.50/1.00 C.Centralized control集中控制 D.Global views全局视野
6多选(1分)To simulate the flocking behavior of birds, the rules
? D.Both of multi-effector problem and multi-body
problem is a multi-agent problem.多效用器和多躯体这两者都是多智能体问题。
2多选(1分)Select the following correct features regarding classical planning.选择如下有关经典规划的正确特征。得分/总分
? A.Keeping a deterministic action at a time.每次保
should consist of要仿真鸟群的群体行为，其规则应包括：得分/持确定性的动作。0.50/1.00
? B.One agent with only one known initial state.一个
智能体仅有一个已知的初始状态。0.50/1.00
? C.Keeping a nondeterministic action at a time.每
次保持不确定性的动作。
? D.Fully observable in a dynamic environment.动
态环境中完全可观测。
3多选(1分)Which of the following approaches are used for classical planning?下列方法中哪些可用于经典规划？得分/总分
? A.Boolean satisfiability布尔可满足性0.25/1.00 ?
B.first-order logical deduction一阶逻辑推理
0.25/1.00
? C.constraint satisfaction约束满足0.25/1.00 ?
D.plan refinement规划精进0.25/1.00
4多选(1分)Planners used in real world for planning and scheduling are more complex, so that select the following correct things which should be extend:现实世界中用于规划和调度的规划者更为复杂，因此选择以下哪些应该扩展。得分/总分
? A.the representation language表示语言0.50/1.00 ?
B.the way to interact with environment与环境交互
的方式0.50/1.00
? C.the planning algorithms规划算法
?
D.the approach used for planning用于规划的途径
总分
? A.Cohesion聚集0.33/1.00 ? B.Separation分离0.33/1.00 ?
C.Communication通信 ?
D.Alignment对齐0.33/1.00
7填空(1分)There are two approaches to searching for a plan, one is ________________ search, and the other is backward relevant-states search.有两种搜索计划的方式，一个是_____________搜索，而另一个是后向状态空间搜索。 前向状态空间 1.00/1.00
8填空(1分)Markov Decision Process (MDP) is a
_______________ process, means action outcomes depend
only on the current state.马可夫决策过程（MDP）是一种
_______________过程，意味着动作结果仅仅依赖于当前状态。离散时间随机控制 1.00/1.00
9填空(1分)There are two optimal policies for Dynamic
Programming, one is ______________, and the other is policy iteration.动态规划有两种优化策略，一个是___________，而另一种是策略迭代。 值迭代 1.00/1.00 Quizzes for Chapter 9
1单选(1分)Which of the following is used to discover general
facts from training examples?下列中哪个用于从训练样本中发现一般的事实？得分/总分
? A.Inductive learning归纳学习1.00/1.00 ? B.Supervised learning有监督学习
?
C.None of the above is correct以上都不正确
? D.Unsupervised learning无监督学习
2单选(1分)There is a set of Web pages identified as interested or uninterested for the user that can be used to solve Web pages filtering problem by machine learning, select which of the following element/feature is the formal definition for those Web pages.有一组供用户标识为感兴趣或不感兴趣的网页，可被机器学习用来解决网页过滤问题，选择下列特征中哪个是通过训练这些网页学来的？得分/总分
? ?
C.Connectionism联结主义0.33/1.00 D.Subjectivism主观主义
6多选(1分)Select the following true phrases regarding the tasks that have been solved by machine learning.选择下列哪些属于可以通过机器学习解决的任务。得分/总分
? ? A.Clustering聚类该题无法得分/1.00 B.Partition划分该题无法得分/1.00 ? A.Task (T)任务 ? B.Examples (E)样本
? C.Experience (E)经验1.00/1.00 ?
D.Performance (P)性能
3单选(1分)Which of the following is used for learned features?以下哪一个是可用于从图像中识别视觉模式的深度神经网络？得分/总分
? A.CNNCNN1.00/1.00
? B.SVMSVM
? C.SIFTSIFT ?
D.OCROCR
4多选(1分)Select the following true algorithms (methods) which have been invented in machine learning?选择下列哪些是机器学习中发明的算法（方法）？得分/总分
? A.Perceptron感知机该题无法得分/1.00 ? B.Decision Tree决策树
? C.Random Forests随机森林
?
D.Generalization泛化该题无法得分/1.00
5多选(1分)Select the following true parties regarding the three parties of machine learning.选择如下哪些派别是有关机器学习的三个派别？得分/总分
? A.Behaviorism行为主义0.33/1.00 ?
B.Symbolicism符号主义0.33/1.00
?
C.Regression回归 ?
D.Classification分类
7多选(1分)Select the following true phrases regarding the
typical paradigms in machine learning.选择下列哪些是典型的机器学习范式。得分/总分
? A.Informal learning非正式学习
?
B.Supervised learning有监督学习0.33/1.00 ?
C.Unsupervised learning无监督学习0.33/1.00 ?
D.Reinforcement learning强化学习0.33/1.00
1单选(1分)Which of the following is used to discover general
facts from training examples?下列中哪个用于从训练样本中发现一般的事实？得分/总分
? A.Unsupervised learning无监督学习 ? B.None of the above is correct以上都不正确 ?
C.Supervised learning有监督学习 ?
D.Inductive learning归纳学习1.00/1.00
2单选(1分)There is a set of Web pages identified as interested
or uninterested for the user that can be used to solve Web pages filtering problem by machine learning, select which of the following element/feature is the formal definition for those Web pages.有一组供用户标识为感兴趣或不感兴趣的网页，可被机器学习用来解决网页过滤问题，选择下列特征中哪个是通过训练这
些网页学来的？得分/总分
? A.Examples (E)样本
? ? ?
B.Performance (P)性能 C.Task (T)任务
D.Experience (E)经验1.00/1.00
3单选(1分)Which of the following is used for learned features?以下哪一个是可用于从图像中识别视觉模式的深度神经网络？得分/总分
? D.Partition划分
7多选(1分)Select the following true phrases regarding the typical paradigms in machine learning.选择下列哪些是典型的机器学习范式。得分/总分
? ?
A.Supervised learning有监督学习0.33/1.00 B.Unsupervised learning无监督学习0.33/1.00 C.Augmented learning增强学习
? A.CNNCNN1.00/1.00 ? ? B.SURFSURF ? C.SIFTSIFT ?
D.LBPLBP
4多选(1分)Select the following true algorithms (methods) which have been invented in machine learning?选择下列哪些是机器学习中发明的算法（方法）？得分/总分
? A.Random Forests随机森林 ? B.Decision Tree决策树0.25/1.00
? C.AdaBoost自适应提升
?
D.Perceptron感知机0.25/1.00
5多选(1分)Select the following true parties regarding the three parties of machine learning.选择如下哪些派别是有关机器学习的三个派别？得分/总分
? A.Symbolicism符号主义0.33/1.00 ? B.Logicalism逻辑主义
? C.Behaviorism行为主义0.33/1.00 ?
D.Connectionism联结主义0.33/1.00
6多选(1分)Select the following true phrases regarding the tasks that have been solved by machine learning.选择下列哪些属于可以通过机器学习解决的任务。得分/总分
? A.Regression回归
? B. Clustering聚类0.33/1.00 ?
C. Classification分类0.33/1.00
?
D.Reinforcement learning强化学习0.33/1.00
8填空(1分)Machine learning is a ______ of artificial intelligence, concerns the construction and study of systems that can learn
from data.机器学习是人工智能的一个______，从事构建和研究可以从数据中学习的系统。 分支 1.00/1.00 Quizzes for Chapter 10
1单选(1分)Which statement best describes the task of “classification” in machine learning?哪一个是机器学习中“分类”任务的准确描述？得分/总分
?
A.To group data objects.对数据对象进行分组。 ?
B.To assign a category to each item.为每个项目
分配一个类别。1.00/1.00
? C.To predict a real value for each item.预测每个项
目实际的值。
? D.To simplify inputs by mapping them into a lower
space.将其映射到低维空间来简化输入。
2单选(1分)Which statement best describes the task of “regression” in machine learning?哪一个是机器学习中“回归”任务的准确描述？得分/总分
? A.To predict a real value for each item.预测每个项
目实际的值。1.00/1.00
? B.To simplify inputs by mapping them into a lower
space.将其映射到低维空间来简化输入。
?
C.To assign a category to each item.为每个项目
分配一个类别。
? D.To order items according to some criterion.依据
某个准则对项目进行排序。
6单选(1分)Which statement best describes the task of “dimensionality reduction” in machine learning?哪一个是机器学习中“降维”任务的准确描述？得分/总分
3单选(1分)Which statement best describes the task of “ranking” in machine learning?哪一个是机器学习中“排名”任务的准确描述？得分/总分
? A. To order items according to some criterion.
依据某个准则对项目进行排序。
? A.To order items according to some criterion.依据
某个准则对项目进行排序。1.00/1.00
? B.To predict a real value for each item.预测每个项
目实际的值。
? B.To assign a category to each item.为每个项目
? C.To simplify inputs by mapping them into a lower
分配一个类别。
? C.To predict a real value for each item.预测每个项
目实际的值。
? D.To find the distribution of inputs in some space.
发现某个空间中输入的分布。
4单选(1分)Which statement best describes the task of “clustering” in machine learning?哪一个是机器学习中“聚类”任务的准确描述？得分/总分
? A. To predict a real value for each item.预测每个
项目实际的值。
? B.To simplify inputs by mapping them into a lower
space.将其映射到低维空间来简化输入。
? C.To assign a category to each item.为每个项目
分配一个类别。
?
D.To group data objects.对数据对象进行分组。
1.00/1.00
5单选(1分)Which statement best describes the task of “density estimation” in machine learning?哪一个是机器学习中“密度估计”任务的准确描述？得分/总分
? A.To group data objects.对数据对象进行分组。
?
B.To find the distribution of inputs in some space.
发现某个空间中输入的分布。1.00/1.00
? C.To predict a real value for each item.预测每个项
目实际的值。
? D.To order items according to some criterion.依据
某个准则对项目进行排序。
space.将其映射到低维空间来简化输入。1.00/1.00
? D.To group data objects.对数据对象进行分组。
7填空(1分)The output of regression is a real ______ value, and the output of classification is a discrete categories.回归的输出是一个实际的______值，而分类的输出则是一个离散的类别。 连续 1.00/1.00
8填空(1分)Clustering is to identify similar groups for input objects _____ training data, and classification is to assign pre-defined classes for input items with training data.聚类是为输
入对象标识相似的组，_____训练数据；而分类则是给输入项分派预定义的类，有训练数据。 没有 1.00/1.00 Quizzes for Chapter 11
1单选(1分)Which statement best describes the paradigm of “Supervised learning” in machine learning?哪一个是机器学习中“有监督学习”范式的准确描述？得分/总分
? A.It receives exclusively unlabeled data and
makes predictions for all unseen data.仅仅接收未标注数据并对所有的未知数据做出预测。
? B.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
?
C.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未
知数据做出预测。 1.00/1.00
? D.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
2单选(1分)Which statement best describes the paradigm of “semi-supervised learning” in machine learning?哪一个是机器学习中“半监督学习”范式的准确描述？得分/总分
? B. It aims to learn some information using a
limited amount of training examples.旨在采用有限数量的训练样本来学习一些信息。1.00/1.00
? A.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
? C.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。1.00/1.00
? C.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
? D.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
3单选(1分)Which statement best describes the paradigm of “unsupervised learning” in machine learning?哪一个是机器学习中“无监督学习”范式的准确描述？得分/总分
? A.It receives exclusively unlabeled data and
makes predictions for all unseen data.仅仅接收未标注数据并对所有的未知数据做出预测。1.00/1.00
? B.It is able to solve a task despite not having
received any training examples of that task.
能够求解一个任务，即使没有得到该任务的任何训练样本。
? C.It aims to learn some information using a limited
amount of training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
? D.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
4单选(1分)Which statement best describes the paradigm of “weakly supervised learning” in machine learning?哪一个是机器学习中“弱监督学习”范式的准确描述？得分/总分
? A.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
? D.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
5单选(1分)Which statement best describes the paradigm of “one-shot learning” in machine learning?哪一个是机器学习中“一次性学习”范式的准确描述？得分/总分
? A.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
? C.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。1.00/1.00
? D.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
6单选(1分)Which statement best describes the paradigm of “zero-shot learning” in machine learning?哪一个是机器学习中“零次性学习”范式的准确描述？得分/总分
? A.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
? C.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
? D.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。1.00/1.00
7单选(1分)Which learning paradigm does it apply storing knowledge to a different but related problem?那种学习范式把储备的强知识用于不同但相关的问题？得分/总分
? D.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。1.00/1.00
2单选(1分)Which statement best describes the paradigm of “semi-supervised learning” in machine learning?哪一个是机器学习中“半监督学习”范式的准确描述？得分/总分
? ? A.Collaborative learning协同式学习 B.Active learning主动式学习 ? A.It aims to learn some information using a limited
amount of training examples.旨在采用有限数量的训练样本来学? C.Ensemble learning集成学习 ?
D.Transfer learning迁移学习1.00/1.00
8多选(1分)Select the following true algorithms (methods) in which each one has been invented as an algorithm (method) of reinforcement learning?选择下列哪些算法（方法）已被发明为专门用于强化学习的算法。得分/总分
? A.Deep Network深度网络该题无法得分/1.00 ?
B.Neural Episodic Control神经情景控制该题无法
得分/1.00
? C.Asynchronous Advantage Actor-Critic异步优势
动作者?评论者该题无法得分/1.00
? D.Deterministic Policy Gradients确定性策略梯度
该题无法得分/1.00
1单选(1分)Which statement best describes the paradigm of “Supervised learning” in machine learning?哪一个是机器学习中“有监督学习”范式的准确描述？得分/总分
? A.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
? B. It aims to learn some information using a
limited amount of training examples.旨在采用有限数量的训练样本来学习一些信息。
? C.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
习一些信息。
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。1.00/1.00
? C. It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
? D.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
3单选(1分)Which statement best describes the paradigm of
“unsupervised learning” in machine learning?哪一个是机器学习中“无监督学习”范式的准确描述？得分/总分
? A.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
? B.It receives exclusively unlabeled data and
makes predictions for all unseen data.仅仅接收未标注数据并对所有的未知数据做出预测。1.00/1.00
? C. It aims to learn some information using a
limited amount of training examples.旨在采用有限数量的训练样本来学习一些信息。
? D.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
4单选(1分)Which statement best describes the paradigm of “weakly supervised learning” in machine learning?哪一个是机器学习中“弱监督学习”范式的准确描述？得分/总分
? A.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。
? C.It aims to learn some information using a limited
amount of training examples.旨在采用有限数量的训练样本来学习一些信息。
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
? D.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
7单选(1分)Which learning paradigm does it apply storing ? C.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。
? D.It aims to learn some information using a limited
amount of training examples.旨在采用有限数量的训练样本来学习一些信息。1.00/1.00
5单选(1分)Which statement best describes the paradigm of “one-shot learning” in machine learning?哪一个是机器学习中“一次性学习”范式的准确描述？得分/总分
? A.It receives exclusively unlabeled data and
makes predictions for all unseen data.仅仅接收未标注数据并对所有的未知数据做出预测。
? B.It aims to learn some information from one, or
only a few, training examples.旨在从一个、或仅有的几个训练样本中学习一些信息。1.00/1.00
? C.It receives a set of labeled data and makes
predictions for all unseen data.接收一组标注数据并对所有的未知数据做出预测。
? D.It aims to learn some information using a limited
amount of training examples.旨在采用有限数量的训练样本来学习一些信息。
6单选(1分)Which statement best describes the paradigm of “zero-shot learning” in machine learning?哪一个是机器学习中“零次性学习”范式的准确描述？得分/总分
? A.It is able to solve a task despite not having
received any training examples of that task.能够求解一个任务，即使没有得到该任务的任何训练样本。1.00/1.00
? B.It is a class of supervised learning that also
make use of unlabeled data for training.属于有监督学习算法一类，此外还利用未标记数据进行训练。
knowledge to a different but related problem?那种学习范式把储
备的强知识用于不同但相关的问题？得分/总分
? A.Collaborative learning协同式学习 ? B.Ensemble learning集成学习 ? C.Transfer learning迁移学习1.00/1.00 ?
D.Active learning主动式学习
8多选(1分)Select the following true algorithms (methods) in
which each one has been invented as an algorithm (method) of reinforcement learning?选择下列哪些算法（方法）已被发明为专门用于强化学习的算法。得分/总分
?
A.Deterministic Policy Gradients确定性策略梯度
0.33/1.00
? B.Behaviorist Psychology行为学派心理学 ?
C.Asynchronous Advantage Actor-Critic异步优势
动作者?评论者0.33/1.00
? D.Neural Episodic Control神经情景控制0.33/1.00
Quizzes for Chapter 12
1多选(1分)Select the following true words in which each one has been invented as a typical learning model for machine learning.从如下模型中选择已被用作机器学习的代表性模型。得分/总分
? A.Networked model网络化模型0.33/1.00 ? B.Probabilistic model概率模型0.33/1.00 ? C.Logical model逻辑模型0.33/1.00 ?
D.Lifecycle model生命周期模型
2多选(1分)Select the following true phrases in which each one has been invented as a probabilistic model for machine learning. 从如下短语中选择已被用作机器学习的概率模型。得分/总分
? ?
0.33/1.00
C.Long short-term memory长短期记忆0.33/1.00 D.Convolutional neural network卷积神经网络
? ?
0.25/1.00
A.Gaussian processes高斯过程0.25/1.00 B.Hidden Markov models隐藏马可夫模型
6填空(1分)The probabilistic model is to use probability theory to express all ________________.概率模型是采用概率论来表示所有________________。
C.Probabilistic program概率规划0.25/1.00 D.Naive Bayes and Bayes Network朴素贝叶斯和
不确定性的形式 1.00/1.00
7填空(1分)A geometric model is constructed directly in instance
? ?
space which can be thought as the ________________ such as 贝叶斯网络0.25/1.00
3多选(1分)Which of the following algorithms are true ones used by manifold learning?下列哪些是真正被流形学习所使用的算法？得分/总分
?
A.SVM (Support Vector Machine)SVM（支撑向量
机）
?
B.PCA (Principal Component Analysis)PCA（主成
分分析）
?
C.LE (Laplacian Eigenmaps)LE（拉普拉斯特征映
射）0.50/1.00
?
D.Isomap (Isometric mapping)Isomap（等距映射）
0.50/1.00
4多选(1分)Select the following phrases in which each one has truly been invented or used as a logical model for machine learning.从如下短语中选择真正地被发明为或被用作机器学习逻辑模型的方法。得分/总分
? A.Association rules关联规则0.33/1.00
? B.First-order logic一阶逻辑0.33/1.00
? C.Linear regression线性回归
?
D.Decision tree决策树0.33/1.00
5多选(1分)Which of the following phrases are the artificial neural networks truly used in machine Learning?下列短语哪些是真正用于机器学习的人工神经网络？得分/总分
? A.Wireless network无线网络
?
B.Deep auto-encoder深度自动编码器0.33/1.00
Euclidean space or Riemannian space.几何模型直接在实例空间构建，该空间可被认为是________________，例如：欧几里德空间或黎曼空间。 几何的概念 1.00/1.00
8填空(1分)The logical models are defined in terms of easily interpretable ______________, or can be easily translated into
rules that are understandable by humans.逻辑模型被定义为易
于解释的______________，或者易于转换成人类能够理解的规则。
逻辑表达式 1.00/1.00
9填空(1分)An artificial neural network is an artificial
representation of the ____________ that tries to simulate its learning processing. 人工神经网络是一种____________的人工表示，试图仿真其学习过程。 人脑 1.00/1.00
1多选(1分)Select the following true words in which each one has been invented as a typical learning model for machine learning.从如下模型中选择已被用作机器学习的代表性模型。得分/总分
?
A.Logical model逻辑模型0.25/1.00 ?
B.Networked model网络化模型0.25/1.00 ?
C.Probabilistic model概率模型0.25/1.00 ?
D.Geometric model几何模型0.25/1.00
2多选(1分)Select the following true phrases in which each one has been invented as a probabilistic model for machine learning.从如下短语中选择已被用作机器学习的概率模型。得分/总分
?
A.Gaussian processes高斯过程0.25/1.00
?
0.25/1.00
B.Hidden Markov models隐藏马可夫模型?
D.Long short-term memory长短期记忆0.33/1.00
? ?
C.Probabilistic program概率规划0.25/1.00 D.Naive Bayes and Bayes Network朴素贝叶斯和
贝叶斯网络0.25/1.00 3 多选(1分)
Which of the following algorithms are true ones used by manifold learning?下列哪些是真正被流形学习所使用的算法？得分/总分
? A.LE (Laplacian Eigenmaps)LE（拉普拉斯特征映
射）0.50/1.00
?
分分析）
B.PCA (Principal Component Analysis)PCA（主成
?
0.50/1.00
C.Isomap (Isometric mapping)Isomap（等距映射）
?
机）
D.SVM (Support Vector Machine)SVM（支撑向量
4多选(1分)Select the following phrases in which each one has truly been invented or used as a logical model for machine learning.从如下短语中选择真正地被发明为或被用作机器学习逻辑模型的方法。得分/总分
? ? ? ?
A.First-order logic一阶逻辑0.33/1.00 B.Adaptive boosting自适应性提升 C.Decision tree决策树0.33/1.00 D.Association rules关联规则0.33/1.00
5多选(1分)Which of the following phrases are the artificial neural networks truly used in machine Learning?下列短语哪些是真正用于机器学习的人工神经网络？得分/总分
? ? ?
A.Deep auto-encoder深度自动编码器 B.Convolutional neural network卷积神经网络 C.Wireless network无线网络