人工智能英语教程参考试卷.docx

《人工智能英语教程参考试卷.docx》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.docx（9页珍藏版）》请在淘文阁 - 分享文档赚钱的网站上搜索。

1、参考试卷二、根据给出的中文意思，写出英文单词（每题0.5分，共10分）写出以下单词的中文意思（每题0.5分，共10分）1accuracy11customize2actuator12definition3adjust13defuzzification4agent14deployment5algorithm15effector6analogy16entity7attribute17extract8backtrack18feedback9blockchain19finite10cluster20framework1 v.收集，adj.嵌入的，内置的n.指示器；指标n.基础设施，基础架构2 v.合并；

2、集成n.解释器，解释程序n.迭代；循环n.库3 一 n.兀数据v,监视；控制;监测11121314151617181920n.神经元；神经细胞n.节点V.运转；操作n.模式v.觉察，觉察n.前提adj濯序的；过程的n.回归adj.健壮的，强健的; 结实的v.筛选三、根据给出的短语，写出中文意思（每题1分，共10分）1 data object2 cyber security3 smart manufacturing4 clustered system5 data visualization6 open source7 analyze text8 cloud computing9 computat

3、ion power10 object recognition基于正确的预测评估模型的性能。2.无监督算法与监督模式算法使用训练和测试集相反，这些算法使用分组方式。他们观察数据中的模 式，并根据其特征（例如维度）的相似性对其进行分组以进行预测。假设我们有一篮子各种 水果，例如苹果、橙子、梨和樱桃。假设我们不知道水果的名称，我们将数据保存为未标记。 现在，假设我们遇到一种情况，有人让我们来确定添加到购物篮中的一种新水果。在这种情 况下，我们使用被称为聚类的概念。 聚类组合或分组具有相同功能的工程。 以前的知识不能用来识别新工程。 他们使用机器学习算法，例如分层和k-mans聚类。 根据新对象的特征

4、或属性，将其分配给一个组以进行预测。四、根据给出的中文意思，写出英文短语（每题1分，共10分）1 数据结构2 决策树3 演绎推理4 贪婪最正确优先搜索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，回答以下问题(每题2分，共10分)Artificial Neural Network (ANN)An artificial neural network (ANN) is

5、the piece of a computing system designed to simulate the way the human brain analyzes and processes information. It is the foundation of artificial intelligence (AI) and solves problems that would prove impossible or difficult by human or statistical standards. ANNs have self-learning capabilities t

6、hat enable them to produce better results as more data becomes available.Artificial neural networks are built like the human brain, with neuron nodes interconnected like a web. The human brain has hundreds of billions of cells called neurons. Each neuron is made up of a cell body that is responsible

7、 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 are interconnected by nodes. These processing units are made up of input and output units. The input units rece

8、ive 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 output report. Just like humans need rules and guidelines to come up with a result or output, ANNs also use a set of learning

9、 rules called backpropagation, an abbreviation for backward propagation of error, 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 supervised phase, the network compares

10、its actual output produced with what it was meant to produce the desired output. The difference between both outcomes is adjusted using backpropagation. This means that the network works backward, going from the output unit to the input units to adjust the weight of its connections between the units

11、 until the difference between the actual and desired outcome produces the lowest possible 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 into the network.Hidden layer - To determine the activity of

12、each hidden unit. The activities of the input units and the weights on the connections between the input and the hidden units. There may be one or more hidden layers.Output layer - The behavior of the output units depends on the activity of the hidden units and the weights between the hidden and out

13、put 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、将以下词填入适当的位置(每词只用一次)。(每题10分，共20分) 填空题1供选择的答案:transactionsinformationtechniqu

14、esfraudnodesunstructuredsubsetsharedautomatedexplosionDeep LearningWhat Is Deep Learning?Deep learning is an artificial intelligence (AI) function that imitates the workings of the human brain in processing data and creating patterns for use in decision making. Deep learning is a 1 of machine learni

15、ng 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.1. How Does Deep Learning Work?Deep learning has evolved hand-in-hand with the digital era, which has brought about an 3 of data

16、in all forms and from every region of the world. This data, known simply as big data, is drawn from sources like social media, internet search engines, e-commerce platforms, and online cinemas, among others. This enormous amount of data is readily accessible and can be 4 through fintech applications

17、 like cloud computing.However, the data, which normally is unstructured, is so vast that it could take decades for humans 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 AI

18、systems for 6 support.2. Deep Learning vs. Machine LearningOne of the most common AI7used for processing big data is machine learning, aself-adaptive algorithm that gets increasingly better analysis and patterns with experience or with newly added data.If a digital payments company wanted to detect

19、the occuirence or potential 8 in itssystem, it could employ machine learning tools for this purpose. The computational algorithm built into a computer model will process all 9 happening on the digital platform, find patterns in the data set, and point out any anomaly detected by the pattern.Deep lea

20、rning utilizes a hierarchical level of artificial neural networks to carry out the process of machine learning. The artificial neural networks are built like the human brain, with neuron 10 connected together like a web. While traditional programs build analysis withdata in a linear way, the hierarc

21、hical function of deep learning systems enables machines to process 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 details about a pers

22、ons face. These details, such as distance between the 1 or shape of the chin,are then converted into a mathematical representation and compared to data on other faces collected in a face recognition database. The data about a particular face is often called a face template and is distinct from a 2 b

23、ecause its designed to only include 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 face templates 4 in the databa

24、se. These systems will offer up several 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 conditions such as poor lighting, low quality image 5, and

25、suboptinial angle of view (such as in aphotograph taken from above looking down on an unknown person).When it comes to errors, there are two key concepts to understand:A false negative is when the face recognition system fails to 6 match a personsface to an image that is, in fact, contained in a dat

26、abase. In other words, the system will erroneously 7 zero results in response to a query.A false positive is when the face recognition system does match a person9s face to an image in a 8, but that match is actually incorrect. This is when a police officer submits animage of “Joe, but the system err

27、oneously tells the officer that the photo is of “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 bett

28、er if the system fails to identifyyou a few times (false negative) than it is for the system to misidentify other people as you and lets those people unlock your phone (false positive). If the result of a misidentification is that an innocent person goes to jail (like a misidentification in a mugsho

29、t database), then the system should be designed to have as few false positives as possible.六、将下面两篇短文翻译成中文(每题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 that machines can really develop human intell

30、igence and consciousness in the same way that a human in conscious. 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 that refers to the use of advanced algorithms to accompli

31、sh specific problem solving or reasoning tasks that do not encompass the full range of human cognitive abilities.2. FunctionalityFunctions are limited in weak AI as compared to strong AL Weak AI does not achieve self-awareness or demonstrate a wide range of human cognitive abilities that a human may

32、 have. Weak AI refers to systems that are programmed to accomplish a wide range problems but operate within a pre-determined or pre-defined range of functions. Strong AI, on the other hand, refers to machines that exhibit human intelligence. The idea is to develop artificial intelligence to the poin

33、t where human interact with machines that are conscious, intelligent and driven by emotions and self-awareness.3. GoalThe goal of weak AI is to create a technology that allows allows machines and computers to to accomplish specific problem solving or reasoning tasks at a significantly quicker pace t

34、han a human can. But it does not necessarily incorporate any real world knowledge about the world of the problem that is being solved. The goal of strong AI is to develop artificial intelligence to the point where it can be considered true human intelligence. Strong AI is a type of which does not ex

35、ist yet in its true form.短文2Pattern RecognitionPattern Recognition is defined as the process of identifying the trends (global or local) in the given pattern. A pattern can be defined as anything that follows a trend and exhibits some kind of regularity. The recognition of patterns can be done physi

36、cally, mathematically or by the use of algorithms. When we talk about pattern recognition in machine learning, it indicates the use of powerful algorithms for identifying the regularities in the given data. Pattern recognition is widely used in the new age technical domains like computer vision, spe

37、ech recognition, face recognition, etc.There are two types of pattern recognition algorithms in machine learning.1. Supervised AlgorithmsThe pattern recognition in a supervised approach is called classification. These algorithms use a two-stage methodology for identifying the patterns. The first sta

38、ge is the development / construction of the model and the second stage involves the prediction for new or unseen 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 al

39、gorithm such as SVM (Support Vector Machines), decision trees, random forest, etc. The model is trained on the training set 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 fo

40、r pattern make use of training and testing sets, these algorithms use a group by approach. They observe the patterns in the data and group them based on the similarity in their features such as dimension to make a prediction. Lets say that we have a basket of different kinds of fruits such as apples

41、, oranges, pears, and cherries. We assume that we do not know the names of the fruits. We keep the data as unlabeled. Now, suppose we encounter a situation where someone comes and tells us to identify a new fruit that was added to the basket. In such a case we make use of a concept called clustering

42、. Clustering combines or groups items having the same features. No previous knowledge is available for identifying a new item. They use machine 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 a pred

43、iction.参考试卷答案、1写出以下单词的中文意思（每题0.5分，共10分）accuracyn.精确（性），准确（性）11customizeVt.定制，定做；用户化2actuatorn.执行器12definitionn.定义3adjustV.调整，调节；适应；校准13defuzzificationn.逆模糊化，去模糊化4agentn.实体；代理14deploymentn.部署5algorithmn.算法15effectorn.效应器6analogyn.类推16entityn.实体7attributen.属性；性质；特征17extractV.提取，提炼8backtrackvi.回溯18feed

44、backn反应9blockchainn.区块链19finiteadj.有限的；限定的10clusterv.聚集n.团，群，簇20frameworkn.构架；框架；（体系的）结构二、根据给出的中文意思，写出英文单词（每题0.5分，共10分）1 V.收集，gather2 adj.嵌入的，内置的inbuilt3 n.指示器；指标indicator4 n.基础设施，基础架构infrastructure5 V.合并；集成integrate6 n.解释器，解释程序interpreter7 n.迭代；循环iteration8 n.库library9n元数据metadata10 v.监视；控制;监测monit

45、or1 V.收集，gather2 adj.嵌入的，内置的inbuilt3 n.指示器；指标indicator4 n.基础设施，基础架构infrastructure5 V.合并；集成integrate6 n.解释器，解释程序interpreter7 n.迭代；循环iteration8 n.库library9n元数据metadata10 v.监视；控制;监测monitor1 V.收集，gather2 adj.嵌入的，内置的inbuilt3 n.指示器；指标indicator4 n.基础设施，基础架构infrastructure5 V.合并；集成integrate6 n.解释器，解释程序interp

46、reter7 n.迭代；循环iteration8 n.库library9n元数据metadata10 v.监视；控制;监测monitor11n.神经元；神经细胞neuron12n.节点node13V.运转；操作operate14n.模式pattern15v.觉察，觉察perceive16n.前提premise17adj.程序的；过程的procedural18n.回归regression19adj.健壮的，强健的； 结实的robust20V.筛选screen三、根据给出的短语，写出中文意思（每题1分，共10分）四、根据给出的中文意思，写出英文短语（每题1分，共10分）1data object数据

47、对象2cyber security网络平安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1数据结构data structure2决策树decision tree3演绎推理deductive reasoning4贪婪最正确优先搜索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 maintenance