SAS A00-405 Exam Practice Test Instant Access

Question 1

Which statement is TRUE regarding the Topics node in SAS Visual Text Analytics''

AThe term relevancy score ranges front 0 to 1.

BA custom topic assigns a term relevancy score of 1 to each document containing the term.

CYou can split or merge topics

DA single document contains only one topic

Answer : D

Question 2

What are two reasons to use a pooling layer in a Convolution Neural Network (CNN)? (Choose two)

Ato increase granularity of information

Bto make the feature map invariant to transformation

Cto extract features of different spatial scale

Dto extract a summarized value from an area of the image

Answer : A, C

Question 3

Regularization in neural networks represents a set of techniques devised to accomplish what?

AReduce overfitting

BDownsample a feature map

CMinimize the toss function

DCalculate a softmax

Answer : C

Question 4

What computation is performed when applying a neural network with Batch Normalization to test data?

A and o^2 are estimated using an exponentially weighted average across tram and test sets

BNormalizations are applied using parameters learned during testing

CNormalizations are applied using parameters learned during training

D and o^2 are estimated using an exponentially weighted average across test set

Answer : A

Question 5

Assume you are using an addLayer call with dcopout=o. 5 to add a pooling layer into a CNN model What is the outcome of the addLayer call?

AThe values from halt of the output neurons of the pooling layer ate randomly set to zero

BThe output feature map size is increased 2 times on width and height.

CThe values from half of the input neurons to the pooling layer are randomly set to zero

DThe output feature map size is reduced by half on width and height

Answer : A

Question 6

Refer to the exhibit.

The pixel intensity values for the top left corner of a 224x224 grey scale image are provided in Exhibit A This image is provided as input to the convolutional filter (Exhibit B) with equal zero padding of size 2 on all sides

What is the first value in the feature map resulting from applying this filler (cross-correlation operation)?

A186

C10 D. 97

Answer : A

Question 7

Given the code to add a concatenation layer:

Assume the output dimensions (width*depth):

* source layer A 100*100*5

* source layer B 100*100*5

* source layer C 100*100*3

What is the correct dimension of the output of this concatenation layer?

A100'100'13

B300'300'5

C100'100'18

D300'300'13

Answer : C

SAS A00-405 SAS Viya 3.5 Natural Language Processing and Computer Vision Exam Practice Test