0% found this document useful (0 votes)
671 views6 pages

T or F

Uploaded by

Isra Belgacem
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)
671 views6 pages

T or F

Uploaded by

Isra Belgacem
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/ 6
1, Backpropagation makes gradient descent more efficient by mea of dynamic programming © twe © fake Sony Comet Annee Tr 2, In some image and voice fel, Al parforms better than humans, so artificial intallgence has entered the stage of srong artificial fnwaigance, © me © Fate SSS 2, Automatic graph segmentation i one ofthe key technologies of MindSpore. © Tue © false Sorry! Correct Answer: Tee 4, One of the disadvantages of daop leaming i thatthe intexpretabilty is very weak, but i's stil possible te visuabze the model using methods such as Local Interpretable Model-Agnostic Explanations (LIME) © toe © ate Sas 5, Allas series chips need the support of CUDA software package like other GPU accelerator cards, © Wwe © Fake Sorry! Correct nswer: Fae 6, The speed of grid search must be faster than random search 0 me © fatee Sorry! Correct Answer: Fase 7, Ina medial image recognition tet, we usualy are more concemed about the recall rat than the precision ratio when evaluating ‘ode! performance, © we © Fate =e & Voice recognition refers to the recognition of text data as audio data, © Tue © Fake Sorry! Correct Answer: False ‘8. In convolutional neural networks, the convolutional layer can reduce the dimension of feature maps. © The © Fave Sorry! ConectAnswer: Te 10, Laplece smoothing can be used to address the “zero probability" problem in the naive Bayes model, © Twe O Fake Sony! Conect Aner: Te 11, Knowledge graph can be applied to social networking, gene sequencing, and risk control. © we © False Sorry! Correct Answer: eve 12, Softerax can't be used for multiple classification problems. © The © Fave Sorry! Comect Answer: False 13, Da Vinel architecture is the core of the Ascend Al computing engine and Al processor. © Wwe © False Sorry! correct answer: eve 14, Ina feedforward network, neurons in the same layer are connected to each other. © Te © False Sorry! Conect Answer: Fase 15, The generalization error will continue to decrease as the complexity of the model increases. © we © fate Sorry! Correct Answer: False 16, If the metrics parameteris not specifed in ModelLcompile, no loss value will be output. © Tue © Fake Sorry! Comect Answer: False 17, Polynomial regression cannet resolve the nonlinear problem. O we © False Sorry Correct Answer: Fie 18, The biggest differance betucen loli regression and percapton is that logistic regression uses the Sigurd activation function _at the output layer, whereas perceptron uses the sign function In addition neither ofthe two models can restive the XOR problem O tw © tase Sony conc Anat rat 19, The HiAl motile computing platform architecture supports various mainstream front-end frameworks such as Tensrflow and Colle © Ime © ake Soy! Cena Answer: Tue 20, To instal Tensorflow of the GPU version, you need to install CUDA and cuDNNN. © Tne © Fake Sony ! Comet Answer: True 13, Similar to a hidden layer, the quantity of neurons at both an input layer and an output layer of a neural network is @ hyperparameter that can be adjusted. © Twe © False Congratulations\Corect nsw: Fae 14, Cifar10 is a built-in data set of Keras. © Tue O fake ‘Congratulations! Correct Answer: True 19, In the KNN model, a smalll K value may cause model underfitting, O Tue © False ‘Congratulations! Correct Anwer: False 20, Malformed data is not dirty deta. © Tne © False Congratulations! Correct Answer: False 2, PyTorch supports GPU acceleration. O True O Fake Sony ! Correct Answer: True 3, After the image label service is called, only one corresponding label value Is returned. O Tue O False Somy | correct answer: False 4, The Adam optimizer in TensorFiow 2.0 is the built-in optimizer of the Keras module. O Tue O False Sorry | Correct Answer: True 5, Jobs that are Innovative and have high requirements on social capabilities cannot be easly replaced by Al. © we © Fake Sorry! Comect Answer: Tue 7, Logical reasoning is a part of Al. O Tue O False Sorry! Comedt Answer: True 9, Sct-team fa fee software machine learning library for Python thas powerful tools fr data analysis and mining © ws © False sory Comet Ans: Tre 10, HiLens can help small and micro companies reali smart access control. O Tne O False Somy! Correct answer: True 12, Alis the core research area of machine learning. O Tue O False Sorry! Correct Answer: False 16, MindSpore supports GPU acceleration. O Tue O False Sony ! Correct Answer: True

You might also like