Brainscape's Knowledge GenomeTM


Top Flashcards (Certified)
All Flashcards

AI-900 > Study Cards > Flashcards

Study Cards Flashcards

(91 cards)

Start Studying
1
Q

__________ is an automated chat to answer questions about refunds and exchange

A

Conversational AI

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

__________ is when you determine if a photo contains a person

A

Computer vision

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

What would you use to determine if a review is positive or negative?

A

Natural language processing

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

Which of the 4 guiding principles is:

Ensure that AI systems operate as they were originally designed, respond to unanticipated conditions, and resist harmful manipulation.

A

Reliability and safety -

To build trust, it’s critical that AI systems operate reliably, safely, and consistently under normal circumstances and in unexpected conditions. These systems should be able to operate as they were originally designed, respond safely to unanticipated conditions, and resist harmful manipulation.

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

Which of the 4 guiding principles is:

Implementing processes to ensure that decisions made by AI systems can be overridden by humans.

A

Accountability -

The people who design and deploy AI systems must be accountable for how their systems operate. Organizations should draw upon industry standards to develop accountability norms. These norms can ensure that AI systems are not the final authority on any decision that impacts people’s lives and that humans maintain meaningful control over otherwise highly autonomous AI systems.

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

Which of the 4 guiding principles is:

Provide consumers with information and controls over the collection, use, and storage of their data.

A

Privacy and security -
As AI becomes more prevalent, protecting privacy and securing important personal and business information is becoming more critical and complex. With AI, privacy and data security issues require especially close attention because access to data is essential for AI systems to make accurate and informed predictions and decisions about people. AI systems must comply with privacy laws that require transparency about the collection, use, and storage of data and mandate that consumers have appropriate controls to choose how their data is used Reference:

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

What workload type is used for identifying handwritten letters?

A

Computer vision

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

What workload type is used for predicting the sentiment of a social media post?

A

Natural language processing

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

What workload type is used for identifying a fraudulent credit card payment?

A

Anomaly detection

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

What workload type is used for predicting next month’s toy sales?

A

Machine learning (regression)

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

What are the current MS principles for responsible AI?

A

Fairness
AI systems should treat all people fairly.

Reliability and safety
AI systems should perform reliably and safely.

Privacy and security
AI systems should be secure and respect privacy.

Inclusiveness
AI systems should empower everyone and engage people.

Transparency
AI systems should be understandable.

Accountability
People should be accountable for AI systems.

https://www.microsoft.com/en-us/ai/responsible-ai

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

T or F:

Providing an explanation of the outcome of a credit loan application is an example of the MS transparency principle for responsible AI.

A

T

Achieving transparency helps the team to understand the data and algorithms used to train the model, what transformation logic was applied to the data, the +nal model generated, and its associated assets. This information offers insights about how the model was created, which allows it to be reproduced in a transparent way.

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

T or F:

A triage bot that prioritizes insurance claims based on injuries is an example of the MS reliability and safety principle for responsible AI.

A

F

A data holder is obligated to protect the data in an AI system, and privacy and security are an integral part of this system. Personal needs to be secured, and it should be accessed in a way that doesn’t compromise an individual’s privacy.

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

T or F:

An AI solution that is offered at different prices for different sales territories is an example of the MS inclusiveness principle for responsible AI.

A

F

Inclusiveness mandates that AI should consider all human races and experiences, and inclusive design practices can help developers to understand and address potential barriers that could unintentionally exclude people. Where possible, speech-to-text, text-to-speech, and visual recognition technology should be used to empower people with hearing, visual, and other impairments.

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

What MS principle of responsible AI is this:

The system must not discriminate based on gender or race.

A

Fairness

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

What MS principle of responsible AI is this:

Personal data must be visible only to approve.

A

Privacy and security

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What MS principle of responsible AI is this:

Automated decision-making processes must be recorded so that approved users can identify why a decision was made.

A

Transparency

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

_________________ is an independently executable workflow of a complete machine learning task. It helps to standardize the best practices of producing a machine learning model, enables the team to execute at scale, and improves the model building efficiency.

A

An Azure Machine Learning pipeline

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

_________ automates the process of building machine learning models and taking the model to production. This is a complex process. It usually requires collaboration from different teams with different skills. A well-defined machine learning pipeline can abstract this complex process into a multiple steps workflow, mapping each step to a specific task such that each team can work independently.

A

Machine learning operation (MLOps)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

What AI workload is used when an automated chatbot answers questions about refunds & exchanges?

A

Knowledge mining

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

What AI workload is used to determine whether a photo contains a person?

A

Computer vision

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

What AI workload is used to determine whether a review is positive or negative?

A

Natural language processing

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

What machine learning task is used to examine the values of a confusion matrix?

A

Model evaluation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
24
Q

What machine learning task is used to split a date into month, day, and year fields?

A

Feature engineering

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
25
What machine learning task is used to pick temperature and pressure to train a weather model?
Feature selection
26
T or F Automated machine learning is the process of automating the time-consuming, iterative tasks of machine learning model development.
T
27
T or F Automated machine learning can automatically infer the training data from the use case provided.
F
28
T or F Automated machine learning works by running multiple training iterations that are scored and ranked by the metrics you specify.
T
29
T or F Automated machine learning enables you to specify a dataset and will automatically understand which label to predict.
F
30
T or F Labelling is the process of tagging training data with known values.
T In machine learning, if you have labeled data, that means your data is marked up, or annotated, to show the target, which is the answer you want your machine learning model to predict. In general, data labeling can refer to tasks that include data tagging, annotation, classification, moderation, transcription, or processing.
31
T or F You should evaluate a model by using the same data used to train the model.
F
32
T or F Accuracy is always the primary metric used to measure a model's performance.
F Accuracy is simply the proportion of correctly classi+ed instances. It is usually the +rst metric you look at when evaluating a classi+er. However, when the test data is unbalanced (where most of the instances belong to one of the classes), or you are more interested in the performance on either one of the classes, accuracy doesn't really capture the effectiveness of a classi+er.
33
_____________ is a machine learning method that uses data to determine the category, type, or class of an item or row of data.
classification
34
____________, in machine learning, is a method of grouping data points into similar clusters. It is also called segmentation.
✑ Clustering
35
T or F Azure Machine Learning designer provides drag-and-drop visual canvas to build, test, and deploy machine learning models.
T
36
T or F Azure Machine Learning designer enables you to save your progress as a pipeline draft.
T
37
T or F Azure Machine Learning designer enables you to include custom JavaScript functions.
F
38
T or F Automated machine learning implements machine learning solutions without the need for programming experience.
T
39
T or F Automated machine learning provides you with the ability to include custom Python scripts in a training pipeline.
T
40
T or F Automated machine learning provides you with the ability to visually connect datasets and modules on an interactive canvas.
T
41
T or F Organizing documents into groups based on similarities of the text contained in the documents is in an example of clustering.
T
42
T or F Grouping similar patients based on symptoms and diagnostic test results is an example of clustering.
T
43
T or F Predicting whether a person will develop mild, moderate, or severe allergy symptoms based on pollen count is an example of clustering.
F
44
T or F A validation set includes the set of input examples that will be used to train a model.
F
45
T or F A validation set can be used to determine how well a model predicts labels.
T
46
T or F A validation set can be used to verify that all the training data was used to train the model.
F
47
____________ is a machine learning task that is used to group instances of data into clusters that contain similar characteristics. It can also be used to identify relationships in a dataset
Clustering Reference: https://docs.microsoft.com/en-us/dotnet/machine-learning/resources/tasks
48
_______________ is a machine learning task that is used to predict the value of the label from a set of related features.
Regression Reference: https://docs.microsoft.com/en-us/dotnet/machine-learning/resources/tasks
49
Which metric can you use to evaluate a classification model?
true positive rate
50
What are 3 regression/forecasting charts/metrics?
Residuals histogram Predicted v. true Forecast horizon
51
In the most basic sense, ___A_____ refers to prediction of a numeric target. _____B_______ attempts to establish a linear relationship between one or more ____C_____ variables and a numeric outcome, or ____C_____ variable. You use this module to define a ______D_____ method, and then train a model using a labeled dataset. The trained model can then be used to make predictions.
A. regression B. Linear regression C. indenpendent & dependent D. Linear regression
52
___________, in machine learning, is a method of grouping data points into similar clusters. It is also called segmentation. Over the years, many of these types algorithms have been developed. Almost all these algorithms use the features of individual items to find similar items. For example, you might apply one to find similar people by demographics. You might use one with text analysis to group sentences with similar topics or sentiment.
cluster
53
Two-class ________ provides the answer to simple two-choice questions such as Yes/No or True/False.
classification
54
___________ is the calculated probability of a correct image classification.
Accuracy
55
____A________, like regression, is a supervised machine learning technique; and therefore follows the same iterative process of training, validating, and evaluating models. Instead of calculating numeric values like a regression model, the algorithms used to train these models calculate______B________ values for class assignment and the evaluation metrics used to assess model performance compare the predicted classes to the actual classes.
A. Classification B. probability
56
______A________ algorithms are used to train a model that predicts one of two possible labels for a single class. Essentially, predicting true or false. In most real scenarios, the data observations used to train and validate the model consist of multiple feature (x) values and a y value that is either 1 or 0.
Binary classification
57
T or F You train a regression model by using unlabeled data.
F Reference: https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-learning-designer/5-create-training-pipeline
58
T or F The classification technical used to predict sequential numeric data over time.
F Reference: https://docs.microsoft.com/en-us/learn/modules/create-classi+cation-model-azure-machine-learning-designer/introduction
59
T or F Grouping times by their common characteristics is an example of clustering?
T Reference: https://docs.microsoft.com/en-us/learn/modules/create-clustering-model-azure-machine-learning-designer/1-introduction
60
__________ is a supervised machine learning technique used to predict numeric values.
Regression Reference: https://docs.microsoft.com/en-us/learn/modules/create-regression-model-azure-machine-learning-designer/1-introduction
61
T or F For a regression model, labels must be numeric.
T Box1:Yes- For regression problems, the label column must contain numeric data that represents the response variable. Ideally the numeric data represents a continuous scale. Reference: https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/train-model
62
T or F For clustering model, labels must be used.
F No- K-Means Clustering - Because the K-means algorithm is an unsupervised learning method, a label column is optional. If your data includes a label, you can use the label values to guide selection of the clusters and optimize the model. If your data has no label, the algorithm creates clusters representing possible categories, based solely on the data. Reference: https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/train-model https://docs.microsoft.com/en- us/azure/machine-learning/component-reference/k-means-clustering
63
T or F For a classification model, labels must be numeric.
F No- For classification problems, the label column must contain either categorical values or discrete values. Some examples might be a yes/no rating, a disease classification code or name, or an income group. If you pick a noncategorical column, the component will return an error during training. Reference: https://docs.microsoft.com/en-us/azure/machine-learning/component-reference/train-model https://docs.microsoft.com/en- us/azure/machine-learning/component-reference/k-means-clustering
64
Azure's __________ service gives you access to advanced algorithms that process images and return information based on the visual features you're interested in. For example, it can determine whether an image contains adult content, find specific brands or objects, or find human faces.
Computer Vision Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview
65
T or F When creating an object detection model in the Custom Vision service, you must choose a classification type of either Multilabel or Multiclass.
F Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector
66
T or F You can create an object detection model in the Custom Vision service to find the location of content within an image.
T Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector
67
T or F When creating an object detection model in the Custom Vision service, you can select from a set of predefined domains.
T
68
T or F The Custom Vision service can be used to detect objects in an image.
T Box1:Yes- Custom Vision functionality can be divided into two features. Image classification applies one or more labels to an image. Object detection is similar, but it also returns the coordinates in the image where the applied label(s) can be found. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/Custom-Vision-Service/overview
69
T or F The Custom Vision service requires that you provide your own data to train the model.
T Yes- The Custom Vision service uses a machine learning algorithm to analyze images. You, the developer, submit groups of images that feature and lack the characteristics in question. You label the images yourself at the time of submission. Then, the algorithm trains to this data and calculates its own accuracy by testing itself on those same images. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/Custom-Vision-Service/overview
70
____________ is a supervised learning problem: define a set of target classes (objects to identify in images), and train a model to recognize them using labeled example photos.
Image classification https://learn.microsoft.com/en-us/training/modules/get-started-ai-fundamentals/4-understand-computer-vision
71
____________ is a computer vision problem. While closely related to image classification, it performs image classification at a more granular scale. Further, it both locates and categorizes entities within images.
Object detection https://learn.microsoft.com/en-us/training/modules/get-started-ai-fundamentals/4-understand-computer-vision
72
73
74
____________ achieves fine-grained inference by making dense predictions inferring labels for every pixel, so that each pixel is labeled with the class of its enclosing object ore region.
Semantic segmentation https://learn.microsoft.com/en-us/training/modules/get-started-ai-fundamentals/4-understand-computer-vision
75
____________: Check the likelihood that two faces belong to the same person and receive a confidence score.
Face verification Reference: https://azure.microsoft.com/en-us/services/cognitive-services/face/#features
76
_________________: Detect one or more human faces along with attributes such as: age, emotion, pose, smile, and facial hair, including 27 landmarks for each face in the image.
Face detection Reference: https://azure.microsoft.com/en-us/services/cognitive-services/face/#features
77
____________ is the process of automatically extracting handwritten information from paper, scans and other low-quality digital documents.
Handwriting OCR (optical character recognition)
78
____________ applies advanced machine learning to accurately extract text, key-value pairs, tables, and structures from documents.
Form Recognizer
79
Use _________ to quickly identify the main concepts in text. For example, in the text "The food was delicious and there were wonderful staff", it will return the main talking points: "food" and "wonderful staff".
key phrase extraction https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/overview
80
T/F You can use the speech service to transcribe a call to text.
T Reference: https://docs.microsoft.com/en-gb/azure/cognitive-services/text-analytics/overview https://azure.microsoft.com/en-gb/services/cognitive- services/speech-services/
81
T/F You can use the text analytics service to extract key entities from a call transcript.
T Reference: https://docs.microsoft.com/en-gb/azure/cognitive-services/text-analytics/overview https://azure.microsoft.com/en-gb/services/cognitive- services/speech-services/
82
T/F You can use the speech service to translate the audio of a call to a different language.
T Reference: https://docs.microsoft.com/en-gb/azure/cognitive-services/text-analytics/overview https://azure.microsoft.com/en-gb/services/cognitive- services/speech-services/
83
_________ is used for tasks such as sentiment analysis, topic detection, language detection, key phrase extraction, and document categorization.
Natural language processing (NLP) Reference: https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing
84
___________ is the process of determining whether a piece of writing is positive, negative or neutral. Reference:
Sentiment Analysis https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing
85
_____________ is a Speech service feature that converts text to lifelike speech.
Azure Text to Speech
86
T/F You can use the translator service to translate text between languages.
T You can use the translator service to translate text between languages. -- Y The translator service provides multi-language support for text translation, transliteration, language detection, and dictionaries. Speech-to-Text, also known as automatic speech recognition (ASR), is a feature of Speech Services that provides transcription. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/Translator/translator-info-overview https://docs.microsoft.com/en- us/legal/cognitive-services/speech-service/speech-to-text/transparency-note
87
T/F You can use the translator service to detect the language of a given text.
T You can use the translator service to detect the language of a given text. -- Y The translator service provides multi-language support for text translation, transliteration, language detection, and dictionaries. Speech-to-Text, also known as automatic speech recognition (ASR), is a feature of Speech Services that provides transcription. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/Translator/translator-info-overview https://docs.microsoft.com/en- us/legal/cognitive-services/speech-service/speech-to-text/transparency-note
88
T/F You can use the translator service to transcribe audible speech to text.
T The translator service provides multi-language support for text translation, transliteration, language detection, and dictionaries. Speech-to-Text, also known as automatic speech recognition (ASR), is a feature of Speech Services that provides transcription. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/Translator/translator-info-overview https://docs.microsoft.com/en- us/legal/cognitive-services/speech-service/speech-to-text/transparency-note
89
The ____________ service provides multi-language support for text translation, transliteration, language detection, and dictionaries.
translator
90
___________, also known as automatic speech recognition (ASR), is a feature of Speech Services that provides transcription.
Speech-to-Text
91

AI-900 (5 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2025 Bold Learning Solutions. Terms and Conditions