人工智能英语教程参考试卷.pdf

《人工智能英语教程参考试卷.pdf》由会员分享，可在线阅读，更多相关《人工智能英语教程参考试卷.pdf（10页珍藏版）》请在淘文阁 - 分享文档赚钱的网站上搜索。

1、参考试卷一、写出以下单词的中文意思（每小题0.5分，共10分）1accuracy11customize2actuator12 definition3adjust13 defuzzification4agent14 deployment5algorithm15 effector6analogy16 entity7attribute17 extract8backtrack18feedback9blockchain19 finite10 cluster20framework二、根据给出的中文意思，写出英文单词（每小题0.5分，共10分）1V.收集，搜集11n.神经元；神经细胞2adj.嵌入的，内置的

2、12 n.节点3n.指示器；指标13V.运转；操作4n.基础设施，基础架构14n.模式5V.合并：集成15V.察觉，发觉6n.解释器，解释程序16n.前提7n.迭代；循环17 adj.程序的；过程的8n.库18n.回归9n.元数据19 adj.健壮的，强健的;结实的10 v.监视；控制；监测20V.筛选三、根据给出的短语，写出中文意思（每小题1分，共10分）1data object2cyber security3smart manufacturing4clustered system5data visualization6open source7analyze text8cloud compu

3、ting9computation power10object recognition四、根据给出的中文意思，写 出 英 文 短 语（每 小 题1分，共10分）1 数据结构 _2 决策树 _3 演绎推理 _4 贪婪最佳优先搜索 _5 隐藏模式，隐含模式 _6 知识挖掘 _7 逻辑推理 _8 预测性维护 _9 搜索引擎 _10 文本挖掘技术五、写出以下缩略 语 的 完 整 形 式 和 中文意思（每 小 题1分，共10分）缩 略 语 _完整形式 中文意思_1 ANN2 AR3 BFS4 CV5 DFS6 ES7 IA8 KNN9 NLP10 VR六、阅读短文，回 答 问 题(每 小 题2分，共10分

4、)Artificial Neural Network(ANN)An artificial neural network(ANN)is the piece of a computing system designed to simulatethe way the human brain analyzes and processes information.It is the foundation of artificialintelligence(AI)and solves problems that would prove impossible or difficult by human or

5、statistical standards.ANNs have self-learning capabilities that enable them to produce betterresults as more data becomes available.Artificial neural networks are built like the human brain,with neuron nodes interconnectedlike a web.The human brain has hundreds of billions of cells called neurons.Ea

6、ch neuron is madeup of a cell body that is responsible for processing information by carrying information towards(inputs)and away(outputs)from the brain.An ANN has hundreds or thousands of artificial neurons called processing units,which areinterconnected by nodes.These processing units are made up

7、of input and output units.The inputunits receive various forms and structures of information based on an internal weighting system,and the neural network attempts to learn about the information presented to produce one outputreport.Just like humans need rules and guidelines to come up with a result

8、or output,ANNs alsouse a set of learning rules called backpropagation,an abbreviation fbr backward propagation oferror,to perfect their output results.An ANN initially goes through a training phase where it learns to recognize patterns in data,whether visually,aurally,or textually.During this superv

9、ised phase,the network compares itsactual output produced with what it was meant to produce the desired output.The differencebetween both outcomes is adjusted using backpropagation.This means that the network worksbackward,going from the output unit to the input units to adjust the weight of its con

10、nectionsbetween the units until(he difference between the actual and desired outcome produces the lowestpossible error.A neural network may contain the following 3 layers:Input layer-The activity of the input units represents the raw information that can feed intothe network.Hidden layer-To determin

11、e the activity of each hidden unit.The activities of the input unitsand the weights on the connections between the input and the hidden units.There may be one ormore hidden layers.Output layer-The behavior of the output units depends on the activity of the hidden unitsand the weights between the hid

12、den and output units.1.What is an artificial neural network(ANN)?2.What is each neuron made up of?3.Wha do the input units do?4.What does an ANN initially go through?5.How many layers may a neural network contain?What are they?七、将下列词填入适当的位置(每词只用一次)。(每小题10分，共 20分)填空题1供选择的答案:transactionsinformationtec

13、hniquesfraudnodesunstructuredsubsetsharedautomatedexplosionDeep Learning1.What Is Deep Learning?Deep learning is an artificial intelligence(AI)function that imitates the workings of thehuman brain in processing data and creating patterns for use in decision making.Deep learning isa _1_ of machine le

14、arning in artificial intelligence that has networks capable of learningunsupervised from data that is_2_or unlabeled.Also known as deep neural learning or deepneural network.2.How Does Deep Learning Work?Deep learning has evolved hand-in-hand with the digital era,which has brought about an_3_of data

15、 in all forms and from every region of the world.This data,known simply as bigdata,is drawn from sources like social media,internet search engines,e-commerce platforms,andonline cinemas,among others.This enormous amount of data is readily accessible and can be_4_through fintech applications like clo

16、ud computing.However,the data,which normally is unstructured,is so vast that it could take decades forhumans to comprehend it and extract relevant_5_.Companies realize the incredible potentialthat can result from unraveling this wealth of information and are increasingly adapting to AIsystems for_6_

17、support.3.Deep Learning vs.Machine LearningOne of the most common A I_7_used for processing big data is machine learning,aself-adaptive algorithm that gets increasingly better analysis and patterns with experience or withnewly added data.If a digital payments company wanted to detect the occuiTence

18、or potential_8_in itssystem,it could employ machine learning tools for this purpose.The computational algorithmbuilt into a computer model will process all _9_happening on the digital platform,findpatterns in the data set,and point out any anomaly detected by the pattern.Deep learning utilizes a hie

19、rarchical level of artificial neural networks to carry out theprocess of machine learning.The artificial neural networks are built like the human brain,withneuron_10_ connected together like a web.While traditional programs build analysis withdata in a linear way,the hierarchical function of deep le

20、arning systems enables machines toprocess data with a nonlinear approach.填空题2供选择的答案:storedresolutionmatchlookunlockdatabasephotographeyesreturn,identifyingFace RecognitionFace recognition systems use computer algorithms to pick out specific,distinctive detailsabout a persons face.These details,such

21、as distance between the_1_ or shape of the chin,are then converted into a mathematical representation and compared to data on other facescollected in a face recognition database.The data about a particular face is often called a facetemplate and is distinct from a _2_because its designed to only inc

22、lude certain details thatcan be used to distinguish one face from another.Some face recognition systems,instead of positively _3_ an unknown person,aredesigned to calculate a probability match score between the unknown person and specific facetemplates_4_in the database.These systems will offer up s

23、everal potential matches,rankedin order of likelihood of correct identification,instead of just returning a single result.Face recognition systems vary in their ability to identify people under challenging conditionssuch as poor lighting,low quality image_5_,and suboptimal angle of view(such as in a

24、photograph taken from above looking down on an unknown person).When it comes to enors,there are two key concepts to understand:A 6false negative“is when the face recognition system fails to _6_match a personsface to an image that is,in fact,contained in a database.In other words,the system willerron

25、eously_7_zero results in response to a query.A“false positive“is when the face recognition system does match a persons face to animage in a _8_,but that match is actually incorrect.This is when a police officer submits animage of Joe,but the system erroneously tells the officer that the photo is of

26、Jack.”When researching a face recognition system,it is important to_9_closely at the falsepositive“rate and the“false negative rate,since there is almost always a trade-off.For example,if you are using face recognition to_10_ your phone,it is better if the system fails to identifyyou a few times(fal

27、se negative)than it is for the system to misidentify other people as you andlets those people unlock your phone(false positive).If the result of a misidentification is that aninnocent person goes to jail(like a misidentification in a mugshot database),then the systemshould be designed to have as few

28、 false positives as possible.六、将下面两篇短文翻译成中文(每小题10分，共 20分)短 文 1Differences between Strong AI and Weak AI1.MeaningStrong AI is a theoretical form of artificial intelligence which supports the view thatmachines can really develop human intelligence and consciousness in the same way that a humanin consc

29、ious.Strong AI refers to a hypothetical machine that exhibits human cognitive abilities.Weak AI(also known as narrow AI),on the other hand,is a form of artificial intelligence thatrefers to the use of advanced algorithms to accomplish specific problem solving or reasoning tasksthat do not encompass

30、the full range of human cognitive abilities.2.FunctionalityFunctions are limited in weak AI as compared to strong AI.Weak AI does not achieveself-awareness or demonstrate a wide range of human cognitive abilities that a human may have.Weak AI refers to systems that are programmed to accomplish a wid

31、e range problems but operatewithin a pre-determined or pre-defined range of functions.Strong AI,on the other hand,refers tomachines that exhibit human intelligence.The idea is to develop artificial intelligence to the pointwhere human interact with machines that are conscious,intelligent and driven

32、by emotions andself-awareness.3.GoalThe goal of weak AI is to create a technology that allows allows machines and computers toto accomplish specific problem solving or reasoning tasks at a significantly quicker pace than ahuman can.But it does not necessarily incorporate any real world knowledge abo

33、ut the world ofthe problem that is being solved.The goal of strong AI is to develop artificial intelligence to thepoint where it can be considered true human intelligence.Strong AI is a type of which does notexist yet in its true form.短文2Pattern RecognitionPattern Recognition is defined as the proce

34、ss of identifying the trends(global or local)in thegiven pattern.A pattern can be defined as anything that follows a trend and exhibits some kind ofregularity.The recognition of patterns can be done physically,mathematically or by the use ofalgorithms.When we talk about pattern recognition in machin

35、e learning,it indicates the use ofpowerful algorithms for identifying the regularities in the given data.Pattern recognition is widelyused in the new age technical domains like computer vision,speech recognition,face recognition,etc.There are two types of pattern recognition algorithms in machine le

36、arning.1.Supervised AlgorithmsThe pattern recognition in a supervised approach is called classification.These algorithmsuse a two-stage methodology for identifying the patterns.The first stage is the development/construction of the model and the second stage involves the prediction for new or unseen

37、 objects.The key features involving this concept are listed below.Classify the given data into two sets-training set and testing set.Train the model using a suitable machine learning algorithm such as SVM(Support VectorMachines),decision trees,random forest,etc.The model is trained on the training s

38、et and tested on the testing set.The performance of the model is evaluated based on correct predictions made.2.Unsupervised AlgorithmsIn contrast to the supervised algorithms for pattern make use of training and testing sets,these algorithms use a group by approach.They observe the patterns in the d

39、ata and group thembased on the similarity in their features such as dimension to make a prediction.Lets say that wehave a basket of different kinds of fruits such as apples,oranges,pears,and cherries.We assumethat we do not know the names of the fruits.We keep the data as unlabeled.Now,suppose weenc

40、ounter a situation where someone comes and tells us to identify a new fruit that was added tothe basket.In such a case we make use of a concept called clustering.Clustering combines or groups items having the same features.No previous knowledge is available for identifying a new item.They use machin

41、e learning algorithms like hierarchical and k-mans clustering.,Based on the features or properties of the new object,it is assigned to a group to make aprediction.参考试卷答案、写出以下单词的中文意思（每小题0.5分，共10分）1accuracyn.精 确（性），准 确（性）IIcustomizevt.定制，定做；用户化2actuatorn.执行器12 definitionn.定义3adjustV.调整，调节；适应；校准13 defu

42、zzificationn.逆模糊化，去模糊化4agentn.实体；代理14 deploymentn.部署5algorithmn.算法15 effectorn.效应器6analogyn.类推16 entityn.实体7attributen.属性；性质；特征17 extractV.提取，提炼8backtrackvi.回溯18feedbackn反馈9blockchainn.区块链19 finiteadj.有限的；限定的10clusterv.聚集n.团，群，簇20frameworkn.构架；框架；结构（体系的）二、根据给出的中文意思，写出英文单词（每小题0.5分，共10分）1V.收集，搜集gather

43、11n.神经元；神经细胞neuron2adj.嵌入的，内置的inbuilt12n.节点node3n.指示器；指标indicator13V.运转；操作operate4n.基础设施，基础架构 infrastructure14n.模式pattern5v.合并：集成integrate15V.察觉，发觉perceive6n.解释器，解释程序interpreter16 n.前提premise7n.迭代；循环iteration17 adj.程序的；过 程 的 procedural8n.库library18n.回归regression9n.元数据metadata19 adj.健壮的，强健的；robust结实的

44、10 V.监视；控制；监测monitor20V.筛选screen三、根据给出的短语，写出中文意思（每小题1分，共10分）1 data object数据对象2cyber security网络安全3smart manufacturing智能制造4clustered system集群系统5data visualization数据可视化6open source开源7analyze text分析文本8cloud computing云计算9computation power计算能力10object recognition物体识别四、根据给出的中文意思，写出英文短语（每小题1分，共10分）1 数据结构dat

45、a structure2决策树decision tree3演绎推理deductive reasoning4贪婪最佳优先搜索greedy best-first search5隐藏模式，隐含模式hidden pattern6知识挖掘knowledge mining7逻辑推理logical reasoning8预测性维护predictive maintenance9搜索引擎search engine10文本挖掘技术text mining technique五、写出以下缩略语的完整形式和中文意思（每小题1 分，共 10分）缩略语完整形式中文意思1ANNArtificial Neural Network

46、人工神经网络2ARAugmented Reality增强现实3BFSBreadth-First Search宽度优先搜索4CVComputer Vision计算机视觉5DFSDepth-First Search深度优先搜索6ESExpert System专家系统7IAIntelligent Agent智能体8KNNK-Nearest NeighborK最近邻算法9NLPNatural Language Processing自然语言处理10VRVirtual Reality虚拟现实六、阅读短文，回答问题（每小题2 分，共 10分）I.An artificial neural network(AN

47、N)is the piece of a computing system designed to simulate theway the human brain analyzes and processes information.It is the foundation of artificialintelligence(AI)and solves problems that would prove impossible or difficult by human orstatistical standards.2.Each neuron is made up of a cell body

48、that is responsible for processing information by carryinginformation towards(inputs)and away(outputs)from the brain.3.The input units receive various forms and structures of information based on an internal weightingsystem.4.An ANN initially goes through a training phase where it learns to recogniz

49、e patterns in data,whether visually,aurally,or textually.5.A neural network may contain 3 layers.They are input layer,hidden layer and output layer.八、将下列词填入适当的位置（每词只用一次）。（每小题10分，共 20分）填空题1参考答案1 subset,2 unstructured,3 explosion,4 shared,5 information,6 automated,7 techniques,8 fraud,9 transactions,1

50、0 nodes填空题2参考答案1 eyes,2 photograph,3 identifying,4 stored,5 resolution,6 match,7 return,8 database,9 look,10unlock六、将下面两篇短文翻译成中文（每小题10分，共 20分）短 文 1强人工智能与弱人工智能之间的区别1.含义强人工智能是人工智能的一种理论形式,它支持以下观点:机器可以像人类一样有意识，真正地发展人类的智力和意识。强 A I是指一种具有人类认知能力的假想机器。另一方面，弱人工智能（也称为狭义人工智能）是一种人工智能形式，指的是使用高级算法来解决特定的问题或完成推理，而这些