Exam4Training

SAS Institute A00-405 SAS Viya 3.5 Natural Language Processing and Computer Vision Online Training

Question #1

Given these two addLayer action calls:

How many trainable parameters for layer fc2?

  • A . 70
  • B . 1050
  • C . 1020
  • D . 1000

Reveal Solution Hide Solution

Correct Answer: D
Question #2

DRAG DROP

("Note: This is an interactive item Follow the instructions to answer the question Scroll bars may appear it the windows are too smart Each window can be resized by dragging on the 5 circles located between windows)

You are building a CNN for an image classification task

Drag the layers on the left to the slots on the right in the appropriate order (from top to bottom) for this task

You have the number of layers listed below

• Input Layer (1)

• Output Layer (1)

• Convolutional Layer (1)

• Fully Connected Layer (2)

• Pooling Layer (1)

Reveal Solution Hide Solution

Correct Answer:


Question #3

Which option is the correct activation (unction for the output layer in a CNN model trained to classify an image belonging to one of the n classes (CI. C2, C3, , Cn)?

  • A . Sigmoid
  • B . ReLU
  • C . TanH
  • D . Softmax

Reveal Solution Hide Solution

Correct Answer: A
Question #4

Refer to the exhibit.

Exhibit A details the structure of a convolutional model Exhibit B provides details o( each layer in the model The blue arrowed lines represent connections between layers.

What is the depth of the residual layer depicted above’?

  • A . 30
  • B . 60
  • C . 15
  • D . 45

Reveal Solution Hide Solution

Correct Answer: D
Question #5

Which statement is TRUE about importing documents into SAS Visual Text Analytics using the Explore and Visualize Data menu?

  • A . You must include your document collection in a parent folder
  • B . You must convert your document collection to a SAS data set
  • C . You must correct misspelled words in the document collection
  • D . You must store the documents as txt files in a folder

Reveal Solution Hide Solution

Correct Answer: A
Question #6

CASL

Python

Review the code in the CASL and Python tabs The code sets are the same but in different languages Given this code which statement correctly describes this recurrent neural network built by the code set1?

  • A . The RNN assigns a classification to each element in the sequence
  • B . The RNN predicts the next value in a sequence
  • C . The RNN assigns a classification to the entire sequence
  • D . The RNN predicts the previous value in a sequence

Reveal Solution Hide Solution

Correct Answer: A
Question #7

Given the category rule:

Which document would be identified based on the text strings in the answer options?

  • A . The patient was diagnosed with Alzheimer’s disease Side effects include decreased cognitive ability and memory issues
  • B . Side effects include decreased cognitive ability and memory issue
  • C . The patient was diagnosed with Alzheimers disease Side effects include decreased cognitive ability and memory issues
  • D . Alzheimer s side effects include decreased cognitive ability and memory issues

Reveal Solution Hide Solution

Correct Answer: C
Question #8

Which statement is TRUE concerning the "dropout" option?

  • A . It specifies the number of neurons to drop from each layer of the network
  • B . It specifies the percentage of neurons to drop from a given layer of the network
  • C . It specifies the percentage of neurons to drop from the entire network
  • D . It specifies the number of layers to drop from the entire network

Reveal Solution Hide Solution

Correct Answer: B
Question #9

Refer to the Exhibit Tab:

An analyst is trying to find Aviation Safety Reports (ASR) related to taxiway and runway incursions

• She does not know the LITI language

• She finds that 3 of the 14 derived topics have keywords related to incursion incidents.

• She would like to examine documents that discuss incursions from the current ASR document collection

Which strategy will best support the analyst’s goals?

  • A . Use the Concepts node to define an INCURSION concept then include this concept in a category rule in the Categories node to identify documents having the INCURSION concept
  • B . Use the Merge topics feature of the Topics node to combine the 3 topics, add the merged topic as a category, and then use the Categories node to categorize documents with respect to the category rules derived using the merged topic Examine the matched documents for the incursion category rule.
  • C . Save the output data from the Topics results window and use the Explore and Visualize Data component of SAS Viya
  • D . Add each of the 3 individual topics as categories then create a category rule in the Categories node that combines the three topic categories using a Boolean OR operation Examine the matched documents fix the incursion category rule

Reveal Solution Hide Solution

Correct Answer: C
Question #10

Refer to the exhibit.

Which statements are TRUE? (Choose two)

  • A . More proper nouns terms than the pronouns terms are kept
  • B . There are 9 concepts in total
  • C . There are 2 custom concepts
  • D . Most preposition terms are kept

Reveal Solution Hide Solution

Correct Answer: C,D

Question #11

Which action set is needed to upload a picture into memory using SAS?

  • A . LoadActionSet
  • B . Image
  • C . DeepLearn
  • D . Table

Reveal Solution Hide Solution

Correct Answer: C
Question #12

Which concept rule must be used for generating factual extraction within a sentence containing machine learning and text analytics?

A)

B)

C)

D)

  • A . Option A
  • B . Option B
  • C . Option C
  • D . Option D

Reveal Solution Hide Solution

Correct Answer: C
Question #13

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

  • A . to increase granularity of information
  • B . to make the feature map invariant to transformation
  • C . to extract features of different spatial scale
  • D . to extract a summarized value from an area of the image

Reveal Solution Hide Solution

Correct Answer: A,C
Question #14

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?

  • A . 100’100’13
  • B . 300’300’5
  • C . 100’100’18
  • D . 300’300’13

Reveal Solution Hide Solution

Correct Answer: C
Question #15

Given the code:

How many trainable parameters do these lines add to the model

  • A . 25
  • B . 520
  • C . 250
  • D . 500

Reveal Solution Hide Solution

Correct Answer: C
Question #16

Consider the CONCEPT rule:

CONCEPT:red@A

Which choice represents a possible result from this CONCEPT rule?

  • A . Redraw begins with the word red and then matches any set of alpha characters
  • B . Reds, a plural variant of the noun red
  • C . Redness a noun having red as a root word
  • D . Redder, a variant of the adjective red

Reveal Solution Hide Solution

Correct Answer: D
Question #17

CORRECT TEXT

Assume no padding is used for the input.

What is the output feature map size created by the cross-correlation between a three color channel, 10*10 input and a 4"4 filter that has a stride of two?

Enter your numeric answers in the spaces above

Reveal Solution Hide Solution

Correct Answer: 3*3
Question #18

Given the code to score images:

What is the actual batch size?

  • A . 20
  • B . 2
  • C . 40
  • D . 10

Reveal Solution Hide Solution

Correct Answer: D
Question #19

Consider the category rule:

Which statement is TRUE about a document that satisfies this rule?

  • A . It exhibits the topic named INCURSION
  • B . It exhibits one or more of the items used to define the INCURSION concept
  • C . It contains the term "incursion" or any of the stemmed versions of "incursion ‘
  • D . It satisfies a previously defined INCURSION category rule but overrides the primary Boolean operator in the original rule with the OR operator

Reveal Solution Hide Solution

Correct Answer: D
Question #20

An analyst wants to identify terms that might be used as keywords to search a document collection looking for consumer comments related to price Using which SAS Visual Text Analytics node and feature would be most efficient for this business need?

  • A . The "create rule from selected elements" feature for the term price in the Textual Elements pane of the Categories node
  • B . The "matched documents" feature for a custom PRICE concept in the Concepts node
  • C . The term table for a derived PRICE topic in the Topics node
  • D . The "show similarity scores" feature for the term price in the Kept Terms pane of the Text Parsing node

Reveal Solution Hide Solution

Correct Answer: C
Exit mobile version