0% found this document useful (0 votes)
161 views10 pages

Quiz AI1

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
0% found this document useful (0 votes)
161 views10 pages

Quiz AI1

Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 10
‘QUESTION NO: 1 Information theory isa branch of applied mathematics. The main research is to quantity how much information @ ‘signal contains. Who Is the frst to propose information theory? OA Turing B. Simon © © Shannon D. Minsky QUESTION No: 2 What are the reeults returned by the If conditional statements in the Python language? (Multiple choles) Ao B.FALSE Dc. True D. null QUESTION No: 3, Which ofthe following statements about overflow and underflow in numerical calculations Is correct? (Multiple choice) ‘A. Overflow occurs when a large number of levels are approximated as 1P or -1P_ | B. Unéerflow occurs when a large number of levels are approximated as 1P or -1P C. Underflow occurs when the number close to zero Is rounded to 2610 © D. Overflow occurs when the number close to zero 1s rounded to zero ‘QUESTION NO: 4 ‘According to the American Society of Automotive Engineers (SAE) The automatic driving is divided into Which level? ALo-Ls: O B.LiaLs LoL DLL QUESTION NO: 5 In the process of deep learning model training, what are the common optimizers? ‘A. Adagrad. B.Adam . Momentum D.seD ‘QUESTION NO: 6 Which command can be checked Atlas 300 (3000) Whether th sccelerator cardis in place? A.atlas info B. 1spel grepratias © C. tepet | grep'st 00" D. tspel | grep'npu’ QuesmiON No: 7 GBDT Compared with the random forest algorithm, which of the following statements is wrong? 2 A. GBDT Algorithm is easier to underfit than random forest B. GBDT Algorithm is easier to overfit than random forest CC, Random forest is calculated in parallel, while GBDT Can't © D. BOT And random forest are built on CART Based on the tree QUESTION No: 8 Which ofthe following description 18 wrong about the image recognition cloud service? O A. The service identities specific objects euch as skyscrapers, buildings, and ships. B, The service can also identify the sea, city, port and other scenes. CC. The service can perform semantic analysis on the content in the image to extract labels with specific abstract meanings © D. The service can provide object and scene labels and can also provide more conceptual labels. ‘QUESTION No: 9 {As the following, what are the Python language design philosophy? (Multiple Choice) OA Expensive Beautiful © c. Simple D. Explicit, ‘QUESTION NO: 10 Python authors deliberately design very restrictive grammars that make bad programming habits (such as the next line of if statement not indented to the right) cannot be compiled O A. False: B.Tue ‘QUESTION NO: 11 In random forest, what strategy is used to determine the outcome of the final ensemble model? ‘A. Cumulative system B. Find the average . Voting system © D. Cumulative system ‘QUESTION No: 12 ‘The three stages of artificial intelligence include computational intelligence, () , Cognitive intelligence. O A. Perceptual intelligence 8. Weak artfcia! intelligence ©. Strong artificial intelligence D. Behavioral intelligence ‘QUESTION NO: 13 Label when the image remake detection service is called successfully sugestion What's the situation? ‘A. uncertainty GB. TRUE 0 C-eertainty Gi D.FALSE ‘QUESTION No: 14 Which description is wrong about the lambda function of the Python language? (© A. The body of a lambda can be an expression or a block of code (© B. lambda is just an expression, and the function body is much simpler than def. © €. The lambda function accepts only one parameter value . The lambda function can access the parameters inthe global namespace. QUESTION NO: 15 What isthe performance of artificial intelligence inthe stage of perceptual intelligence? {A Machines begin to calculate and transmit information just ike humans OB, The machine starts to understand and understand, make judgments, and take some simple actions © €. Machines begin to understand, think and make decisions like humans ‘QUESTION NO: 16 In deep learning tasks, when encountering data imbalance problems, which of the following methods can we use to solve the problem? © A. Random undersampling B. Synthetic sampling . Random oversampling D. batch deletion ‘QUESTION NO: 17 Which ofthe following are Al Subfleld? ‘A. Computer vision B. Speech Recognition . Natural language processing D. Machine fearning ‘QUESTION NO: 18 Huawei Al The whole scenario includes public cloud, private cloud, various edge computing, loT Industry terminals ‘and consumer. The deployment environment of terminal, edge, and cloud for fee-based terminals. © ATRUE > B. FALSE QUESTION NO: 19 ‘What are the common clustering algorithme? © A.Kmeans © B. Spectral clustering C. Hierarchical clustering D. Density clustering ‘QUESTION NO: 20, GAN isa deep learning model and one of the most promising methods for unsupervised learning in complex distribution in recent years. A.False B. Tue ‘QUESTION NO: 22 "Which ofthe following description about Python regular expression is not correct? © Acre regular expressions can only process string data not numeric data B. re regular expression module gives the Python language all the regular expression functionality. © C. re regular expressions are powerful tools for working with string © D. Python has added there regular expression module since version 1.6. ‘QUESTION NO: 23 In convolutional neural network, different layers have different functions. Which of the following layers can play the role of dimensionality reduction? {A Pooling layer B. Input layer 0 ©. Convolutional ayer D. Fully connected layer ‘QUESTION NO: 24 ‘The Python dictionary is widely identified by "Q". and the internal data consists ofthe key and its corresponding value > A False B True ‘QUESTION NO: 25 Deep learning Isa branch of machine learning A False B. Tue ‘QUESTION NO: 26 What is wrong about the image content review service? {A labet Label representing each test result O B confidence Represents confidence, range 0-100, © C.politics Test results for sensitive persons involved in polities © Di terrorism Test results for political violence ‘QUESTION NO: 27 Which of the fellowing environments does not suppert to Install the THnsorFlow? © A. Linux © B.Mac os © C. Openstack D. Docker ‘QUESTION NO: 28 ‘The following about KNN Algorithm k The value description is correct? CA. can k Value is set too (CB. K The larger the value, the smoother the segmentation surface of the classification OC. Value is a hyperparameter (DK The larger the value, the easier the model is to overft ‘QUESTION NO: 29 What are the advantages of Python? (Multiple cholce) CO AFree OB Simple (DC. High4evel language 0 D-Rieh trary ‘QUESTION NO: 30 ‘Among the machine learning algorithms, the following is not an integrated learning strategy? A. Stacking 0 B. Bagging ©. Marking D. Boosting (QUESTION NO: 31 Which ofthe following does not belong to long-term memory LSTM (long Short“Term Memory) network architecture? ‘A. Output door B. Forget the door © €. Input door D. Memory door ‘QUESTION No: 32 ‘The following belongs to TensorFlow2.0 The characteristic is? A. Support static image mechanism © B Continue to be compatible Tensorflowl x Related modules C. Support more platforms and more languages D. Introduce Keras interface ‘QUESTION NO: 33 Vector is a number. A False B. True ‘QUESTION NO: 34 Which ofthe following are Al Application areas? OA. Smart medical D B.Wisdom education 0 ¢. Smarthome (CD Smart city QUESTION NO: 36 [Lt with L2 Regularization is a method commonly used in traditional machine learning to reduce generalization errors. ‘The following Ie about the two. The right way Is: ‘A.L1 with L2 Regularization can be used for feature selection B. L2 Regularization can do feature selection Lt with L2 Regularization cannot be used for feature selection Lt Regularization can do feature selection QUESTION NO: 36 Which ofthe following i 1 image label service URI? A Iv1.limageleelebrity recognition > B.fv.olimageirecognition > €.Wt.olimagertagging D.iv1.imageirecapture-detect QUESTION No: 37 ‘The number of rows and columns of the three matrices A, B and Cis 3 rows and 2 columns, 2rows. 3 columns. 3 rows and 3 columns, which ofthe following operations is meaningful? ase BAB © c.aB-se D.Ac QUESTION No: 38, Recurrent neural networks can capture dynamic Information in serialized data > AL TRUE © B. FALSE ‘QUESTION NO: 38 ‘What are the commonly used loss functions? (Multiple choice) A. Softmax cross enlt0py B. Sigmoid cross entropy C. Maan variance D. Weighted Stgmotd Cross Entropy E. Sparse cross entropy QUESTION N¢ Which ofthe following are the elements of artificial intelligence? (Multiple choice) © AAlgorithem B.Data C. Computing power D.Scene (QUESTION No: 41 How many spaces does Pf stipulate that Python's first fine indentation needs to indent? At c2 D4 ‘QUESTION NO: 42 X.Y are random variables. C Isa constant. which of the following description about the nature of the mathematical ‘expectation is incorrect? © A.EIC)= CA. E(C)=C BL ERXY) = EXKIEQ) © 6. EDeY) = EOE) D. (Cx) = CEO QUESTION NO: 43, ‘thkeres.datasets Can view keras The builtin data set. ‘AUTRUE © BLFALSE ‘QUESTION No: 44 Which ofthe following activation functions are prone to vanishing gradient problems? OAReLU OB. Softplus Cc. Sigmoia 0 D.Tanh ‘QUESTION No: 45 ‘What are the commonly used gradient descent optimization functions? (Multiple Choice) OA. momentum (OB Adagrad CC RMsProp CD. Adadetta OE. Random gradient descent ‘QUESTION NO: 46 Faced with the challenge of achieving efficient distributed training for ltraarge-scale models, MindSpore handled as? (© A Manual parallel © B. Serial C. Automatic parallel ‘QUESTION No: 47 HIAI Mobile computing platform provides rich upper-level functional services API, Can run efficiently on mobile devices. © A. TRUE FALSE QUESTION NO: 48 ‘The optimizer Is an important part of training neural networks. The purpose of using the optimizer does not include which of the following: © A. Speed up algorithm convergence > B.Avold overfting Reduce the ditficulty of manual parameter setting D. Avoid local extremes ‘QUESTION NO: 48, Inneural networks, weights are often shareD. Which of the following neural networks will share weights? 0 A.Recurrent neural network CB Convolutional Neural Network OC .sensor C D. Fully connected neural network ‘QUESTION NO: 50 ‘The image data of the passport recognition service is not needed base Coded. A TRUE O B. FALSE

You might also like