Quiz questions Flashcards

1
Q

In this computer vision task, individual pixels in an image are classified according to the object to which they belong.
Object Detection
Semantic Segmentation
Image Analysis
Optical Character Recognition
Show Answer

A

Semantic Segmentation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

In this computer vision technique, text can be detected and read in images.

A

Optical Character Recognition

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Which of these can be used to create conversational AI?
Q&A Maker
Semantic Segmentation
Azure Speech Maker
Azure Chat Functions

A

Q&A Maker

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

. Which is not one of the resources that can be created using Azure Machine Learning Studio?
Compute Instances
Compute Balancers
Compute Clusters
Inference Clusters

A

Compute Balancers

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

. Which would be used to predict the category an item belongs to?
Classification
K-means
Clustering
Neural Network

A

Classification

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Which technique is used to group similar entities based on features?
Classification
K-means
Clustering
Neural Network

A

Clustering

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What are the resource types available as Computer Vision service?
Computer Vision and Computer Cluster
Computer Key and Computer Endpoint
Computer Vision and Computer Services
Computer Insights and Computer Services
Show Answer

A

Computer Vision and Computer Services

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What are the two specialised domain models of Computer Vision?
Stars and Places
Marker and People
Background and Landmarks
Celebrities and Landmarks

A

Celebrities and Landmarks

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Which of these metrics is not used when model training in Custom Vision?
Precision
Recall
Mean Average Precision
F1 Score

A

F1 Score

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Which is not a supported image format in the Face Service?
JPEG
AI
PNG
BMP

A

AI (.ai)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

The OCR API returns hierachical information consisting of all of the following, except:
Regions
Areas
Lines
Words

A

Areas

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Translation Text uses which model for translation?
Neural Network
SVM
Cognitive Text
Neural Machine Translation

A

Neural Machine Translation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Which is not an entity type of LUIS application intents?
List
RegEx
Filter
Machine-Learned

A

Filter

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Which is not a machine learning algorithm category?
Classification
Regression
Normalization
Clustering

A

Normalization

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Which is a multiclass classification algorithm?
Decision Forest
K-means
K-nearest Neighbor
Anomaly Detection

A

Decision Forest

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

This is used to highlight the strongest pattern in a dataset:
Reinforcement Learning
Principal Component Analysis
K-means
Classification Algorithm

A

Principal Component Analysis

17
Q

Which is not a supported file format in Azure ML?
Excel
CSV
TSV
XML

A

XML

18
Q

What is the goal of feature engineering?
Update values to use a common scale
Create a smaller set of discrete ranges
Update missing values with other values
Match data against the question

A

Match data against the question

19
Q

The fraction of time when the model is correct is known as:
Precision
Accuracy
Recall
F1 Score

A

Accuracy

20
Q

Which of these confirms how often the model is correct:
Precision
Accuracy
Recall
F1 Score

A

Precision

21
Q

Which value identifies how much the model finds all there is to find?
Precision
Accuracy
Recall
F1 Score

A

Recall

22
Q

This regression type is used to predict a variable that can be considered as a label:
Ordinal
Linear
SVM
Poisson

A

Ordinal

23
Q

This regression type uses counts instead of data values
Ordinal
Linear
SVM
Poisson

A

Poisson

24
Q

. Statistical analysis cab be broken down into these three processes:
Research, testing, deployment
Transformation, Visualisation, Modeling
Workflow, Modeling, Deployment
ETL, ELT, Testing

A

Transformation, Visualisation, Modeling

25
Q

. Which is not a metric for clustering models?
Mean Absolute Error
Average Distance to Cluster Center
Average Distance to Other Center
Number of Points

A

Mean Absolute Error

26
Q

Which is not an offering of Cognitive Services?
3D
Speech
Vision
Language

A

3D

27
Q

Which is a feature of Computer Vision?
Image Stabalization
Tagging Images
Motion Detection
Video Thumbnail

A

Tagging Images

28
Q

According to which principle of responsible AI should AI solutions empower everyone and engage people?
Inclusiveness
Transparency
Accountability
Fairness

A

Inclusiveness

29
Q

ou build a machine learning model by using the automated machine learning user interface (UI).
You need to ensure that the model meets the Microsoft transparency principle for responsible AI.
What should you do?

A

Enable Explain best model

30
Q

what is Explain best model

A

ost businesses run on trust and being able to open the ML black box helps build transparency and trust. In heavily regulated industries like healthcare and banking, it is critical to comply with regulations and best practices. One key aspect of this is understanding the relationship between input variables (features) and model output. Knowing both the magnitude and direction of the impact each feature (feature importance) has on the predicted value helps better understand and explain the model. With model explain ability, we enable you to understand feature importance as part of automated ML runs.
Reference:

31
Q
A