Huawei HCIA Artificial Intelligence Cetification Q and A WRITTEN [PDF]

Zitiervorschau

1. Backpropagation makes gradient descent more efficient by means of dynamic programming. Answer: True

2. In some image and voice fields, AI performs better than humans, so artificial intelligence has entered the stage of strong artificial intelligence. Answer: False

3. Automatic graph segmentation is one of the key technologies of MindSpore. Answer: True

4. One of the disadvantages of deep learning is that the interpretability is very weak, but it is possible to visualize the model using methods such as Local Interpretable Model-Agnostic Explanations (LIME). Answer: True

5. Atlas series chips need the support of CUDA software package like other GPU accelerator cards. Answer: False

6. The speed of grid search must faster than random search. Answer: False

7. In a medical image recognition task, we usually are more concerned about the recall ratio than the precision ratio when evaluating model performance. Answer: True

8. Voice recognition refers to the recognition of text data as audio data. Answer: False

9. In convolutional neural networks, the convolutional layer can reduce the dimension of feature maps. Answer: True

10. Laplace smoothing can be used to address the “zero probability” problem in the naïve Bayes model. Answer: True

11. Knowledge graph can be applied to social networking, gene sequencing, and risk control. Answer: True

12. Softmax can’t be used for multiple classification problems. Answer: False

13. Da Vinci architecture is the core of the Ascend AI computing engine and AI processor. Answer: True

14. In a feedforward network, neurons in the same layer are connected to each other. Answer: False

15. The generalization error will continue to decrease as the complexity of the model increases. Answer: False

16. If the metrics parameter is not specified in Model.compile, no less value will be output. Answer: False

17. Polynomial regression cannot resolve the nonlinear problem. Answer: False

18. The biggest difference between logistic regression and perceptron is that logistic regression uses the Sigmoid activation function at the output layer, whereas perceptron uses the sign function. In addition, neither of the two models can resolve the XOR problem. Answer: True

19. The HiAI mobile computing platform architecture supports various mainstream front-end frameworks, such as TensorFlow and Caffe. Answer: True

20. To install TensorFlow of the GPU version, you need to install CUDA and cuDNN. Answer: True

21. Without Padding, use a 3X3 convolution kernel to convolve a 5X5 image with stride 1. Which of the following options is the size of the output image.? Answer: A. 3X3

22. Which of the following statements about PyTorch is incorrect? Answer: D. PyTorch uses the Lua programming language.

23. Which of the following learning methods is most suitable for training machine learning models of chessboard games? Answer: D. Reinforcement learning

24. Which of the following is the output range of the ReLU function? Answer: A. [0,+∞]

25. Which of the following is not an integrated learning policy in machine learning algorithms? Answer: D. Marking

26. In machine learning, how many support vectors can the SVM algorithm have? Answer: D. Several

27. Input_shape = (4,28,28,1) x = tf.random.normal(input_shape) y = tf.keras.layers.Conv2D(filters=2, kernel_size=3, strides=(1,1), padding=’valid’, activation=’relu’, input_shape=input_shape[1:]) (x) print(y.shape) What is the output of the preceding code? Answer: B. (4,26,26,2)

28. In the process of training the neural network, which of the following methods is used to update the parameters so as to minimize the loss function? Answer: C. Gradient descent

29. Which of the following is a function of HiAI Foundation? Answer: B. Quickly convert and migrate existing models

30. When was the Turing Test proposed? Answer: A. 1950

31. Which of the following options is the artificial intelligence development framework launched by Huawei? Answer: C. MindSpore

32. Which of the following is not a feature of the Atlas 500 AI edge stations? Answer: C. High energy consumption

33. Which of the following is not the model deployment and application feature of the ModelArts platform? Answer: B. Low throughput and low latency

34. adadelt=tf.keras.optimizers.Adadelta() model.compile(loss=’binary_crossentropy’, optimizer=’adam’, metrics=[‘accuracy’]) Which optimizer is used in the above code? Answer: A. Adam

35. Which of the following options is the architecture adopted by Hauwei Atlas series chips? Answer: D. Da Vinci

36. Which of the following is a generative model? Answer: C. Naive Bayes

37. What kind of operation does “concat” represent in TensorFlow 2.0? Answer: A. Merge tensor

38. When tf.keras is used to build a network model, which of the following statements about tf.keras.Model and tf.keras.Sequential is incorrect? Answer: D. If a sharing layer exists on the network, tf.keras.Sequential is recommended for building a model.

39. Which of the following models is not suitable for the scenario where the covariance between data features is large? Answer: C. Naive Bayes

40. How many images are included in the MNIST handwritten digit database in the lab guide? Answer: C. 7,000

41. Which of the following options makes the GPU suitable for the acceleration of neural networks? Answer: B. Parallel computing ability

42. Which of the following is the representative of behaviorism? Answer: D. Reinforcement learning

43. Which of the following statements about ModelArts is incorrect? Answer: A. Supports massive data preprocessing and automatic labeling.

44. Which of the following statements about dropout is incorrect? Answer: D. dropout can’t be added during inference

45. What types of services can deployed on ModelArts? Answer: A,B,C

46. Which of the following are AI applications? Answer: A,B,C,D

47. Compared with the batch gradient descent method, which of the following options are the advantages of the Mini batch gradient descent method? Answer: A & B

48. Suppose the following scenario: Now we need to classify the data, and the data features are all continuous values. Which of the following models are suitable for this scenario? Answer: B & C

49. What are the elements of AI? Answer: A,B,C,D

50. Which of the following are major functions of Mind Expression in MindSpore? Answer: A,B,C,D

51. Which of the following are the problems you may encounter when training a generative adversarial network? Answer: A,B,C,D

52. Which of the following are deep learning frameworks? Answer: A,B,C,D

53. Which of the following options belong to data preprocessing? Answer: A,B,C,D

54. Which of the following are the major modules of the Ascend AI processor? Answer: A,B,C,D

55. Regarding the standard RNN model statement, which of the following options are correct? Answer: A & C

56. Which of the following statements about TensorFlow are correct? Answer: A,B,C

57. Which of the following options belong to the Huawei Cloud EI service? Answer: A,B,C,D

58. Which of the following options are Huawei products? Answer: A,B,C

59. Which of the following statements about LSTM are correct? Answer: A,B,C,D

60. Which of the following are applications scenarios of EI Intelligent Twins? Answer: A,B,C,D