AI-900 (Whole set)

Computer Vision Natural Language Processing Anomaly Detection Machine Learning (Regression) Notes: Computer Vision = identify (object) letters NLP = sentiment Anomaly Detection = fraud Machine Learning (regression) = predict

Choose the workload type that best fits each statement. Each workload type can be used once, more than once, or not at all. Workload Types - Anomaly detection - Computer vision - Machine Learning (Regression) - Natural Language Processing Identify handwritten letters. (Workload type?) Predict the sentiment of a social media post. (Workload type?) Identify a fraudulent credit card. (Workload type?) Predict next month's toy sales. (Workload type?)

labeling

Complete the sentence with the correct term. Assigning classes to images before training a classification model is an example of __________. - evaluation - feature engineering - hyperparameter tuning. - labeling

a reliability and safety

Complete the sentence with the correct term. Ensuring an AI system does not provide a prediction when important fields contain unusual or missing values is __________ principle for responsible AI. - an inclusiveness - a privacy and security - a reliability and safety - a transparency

Feature engineering

Complete the sentence with the correct term. Ensuring that the numeric variables in training data are on a similar scale is an example of ____________. - data ingestion - feature engineering - feature selection - model training

Regression Notes: Sales price is numeric, which means the answer is "regression".

Complete the sentence with the correct term. _____________ models can be used to predict the sale price of auctioned items. - Classification - Clustering - Regression

Randomly split the data into rows for training and rows for evaluation.

For a machine learning progress, how should you split data for training and evaluation? - Use features for training and labels for evaluating. - Randomly split the data into rows for training and rows for evaluation. - Use labels for training and features for evaluation. - Randomly split the data into columns for training and columns for evaluation

No Yes No Notes: No: By essence, a validation set is different from test set. Yes: This is the purpose of a validation set: to validate (or not) the model. No: A validation test doesn't test if all the train split of a dataset has been used to train the model. That's out of scope.

HOTSPOT For each of the following statements, select Yes if the statement is true. A validation set includes the set of input examples that will be used to train a mode. YES/NO A validation set can be used to determine how well a model predicts labels. YES/NO A validation set can be used to verify that all the training data was used to train the model. YES/NO

Yes Yes No Notes: Clustering = similarities

HOTSPOT For each of the following statements, select Yes if the statement is true. Organizing documents into groups based on similarities of the text contained in the documents is an example of clustering. YES/NO Grouping similar patients based on symptoms and diagnostic test results is an example of clustering. YES/NO Predicting whether a person will develop mild, moderate, or severe allergy symptoms based on pollen count is an example of clustering. YES/NO

No Yes No

HOTSPOT For each of the following statements, select Yes if the statement is true. Otherwise, select No. Answer Area Statements Yes No Forecasting housing prices based on historical data is an example of anomaly detection. YES/NO Identifying suspicious sign-ins by looking for deviations from usual patterns is an example of anomaly detection. YES/NO Predicting whether a patient will develop diabetes based on the patient's medical history is an example of anomaly detection. YES/NO

***FILL THIS BACK IN*****

HOTSPOT For each of the following statements, select yes or no if the statement is true. Automated machine learning is the process of automating the time-consuming, iterative tasks of machine learning model development. YES/NO Automated machine learning can automatically infer the training data from the use case provided. YES/NO Automated machine learning works by running multiple training iterations that are scored and ranked by the metrics you specify. YES/NO Automated machine learning enables you to specify a dataset and will automatically understand which label to predict. YES/NO

YES NO NO

HOTSPOT Providing an explanation of the outcome of a credit loan application is an example of the Microsoft transparency principle for responsible AI. YES/NO A triage bot that prioritizes insurance claims based on injuries is an example of the Microsoft reliability and safety principle for responsible AI. YES/NO An AI solution that is offered at different prices for different sales territories is an example of the Microsoft inclusiveness principle for responsible AI. YES/NO

Named Entity Recognition (NER)

HOTSPOT Select the answer that correctly completes the sentence. Answer Area ___________ used to extract dates, quantities, and locations from text. - Key phrase extraction - Language detection - Named Entity Recognition (NER) - Sentiment Analysis

Optical character recognition (OCR)

HOTSPOT Select the answer that correctly completes the sentence. ______________ extracts text from handwritten documents. - Object detection - Facial recognition - Image classification - Optical character recognition (OCR)

Yes Yes No Note: You can make customizations through code but only with Python and R code.

HOTSPOT Select yes if the statement is correct. Azure Machine Learning designer provides a drag-and-drop visual canvas to build, test, and deploy machine learning models. YES/NO Azure Machine Learning designer enables you to save your progress as a pipeline draft. YES/NO Azure Machine Learning designer enables you to include custom JavaScript functions. YES/NO

reliability and safety

HOTSPOT When developing an AI system for self-driving cars, the Microsoft _________ principle for responsible AI should be applied to ensure consistent operation of the system during unexpected circumstances. - inclusiveness - accountability - reliability and safety - fairness

Yes Yes No Notes: Variables or measurements = Features Classifications/True/Falses = Labels

HOTSPOT You have an Azure Machine Learning model that predicts product quality. The model has a training dataset that contains 50,000 records. A sample of the data is shown in the following table: Date Time Mass (kg) Temp (C) Qual. Test 26/02/2021 15:31:07 2.108 62.5 Pass 26/02/2021 15:31:39 2.099 62.4 Pass 26/02/2021 02:32:21 2.098 66.4 Fail For each of the following statements, select Yes if it is true. Mass (kg) is a feature. YES/NO Quality Test is a label. YES/NO Temperature (C) is a label. YES/NO

Yes No No

HOTSPOT Select yes if the answer is correct. Labeling is the process of tagging training data with known values. YES/NO You should evaluate a model by using the same data used to train the model. YES/NO Accuracy is always the primary metric used to measure a model's performance. YES/NO

- Model evaluation - Feature engineering - Feature selection

Match the learning tasks to the appropriate scenarios. Each task may be used once, more than once, or not at all. Statements - Examining the values of a confusion matrix - Splitting a date into month, day, and year fields - Picking temperature and pressure to train a weather model Learning Types - Feature engineering - Feature selection - Model deployment - Model evaluation - Model training

- verification - similarity - grouping - identification

Match the term to the correct statement. Each term can be used once, more than once, or not at all. Statement __________ : Do two images of a face belong to the same person? __________ : Does this person look like other people? __________ : Do all the faces belong together? __________ : Who is this person in this group of people? Answer Area - grouping - identification - similarity - verification

- verification - similarity - identification

Match the term to the correct statement. Each term can be used once, more than once, or not at all. Statement __________ : Do two images of a face belong to the same person? __________ : Does this person look like other people? __________ : Who is this person in this group of people? Answer Area - grouping - identification - similarity - verification

- Facial recognition - Optical character recognition (OCR) - Object detection

Match the term to the correct statement. Each term can be used once, more than once, or not at all. Statement ____________ : Identify celebrities in images. ____________ : Extract movie title names from movie poster images. ____________ : Locate vehicles in images. Answer Area - Facial recognition - Image classification - Object detection - Optical character recognition (OCR)

1. Fairness 2. Privacy and security 3. Transparency

Match the term to the statement that it most accurately describes. Each principle may be used once, more than once, or not at all. Statements 1. The system must not discriminate based on gender, race. 2. Personal data must be visible only to approve. 3. Automated decision-making processes must be recorded so that approved users can identify why a decision was made Principles - Fairness - Privacy and security - Reliability and safety - Transparency

1. Natural language processing (NLP) 2. Computer vision 3. Natural Language processing

Match the types of AI workloads to the appropriate scenarios. Each term can be used once, more than once, or not at all. Statements - An automated chatbot to answer questions about refunds and exchanges. - Determining whether a photo contains a person. - Determining whether a review is positive or negative. Workload Types - Anomaly detection - Computer vision - Knowledge mining - Natural language processing - Computer vision - Knowledge mining - Natural language processing

Yes Yes No Notes: Custom Vision Service can't alone analyze videos.

Select Yes if the statement is correct. The Custom Vision service can be used to detect objects in an image. YES/NO The Custom Vision service requires that you provide your own data to train the model. YES/NO The Custom Vision service can be used to analyze video files. YES/NO

Yes Yes No

Select Yes if the statement is correct. The Face service can be used to perform facial recognition for employees. YES/NO The Face service will be more accurate if you provide more sample photos of each employee from different angles. YES/NO If an employee is wearing sunglasses, the Face service will always fail to recognize the employee. YES/NO

Yes Yes Yes

Select Yes if the statement is correct. You can use the Speech service to transcribe a call to text. YES/NO You can use the Text Analytics service to extract key entities from a call transcript. YES/NO You can use the Speech service to translate the audio of a call to a different language. YES/NO

Yes Yes Yes

Select yes if the statement is true. Automated machine learning provides you with the ability to include custom Python scripts in a training pipeline. YES/NO Automated machine learning implements machine learning solutions without the need for programming experience. YES/NO Automated machine learning provides you with the ability to visually connect datasets and modules on an interactive canvas. YES/NO

- Inclusiveness - Fairness - Reliability and safety Note: The 6 guiding principles are 1. Fairness, 2. Inclusiveness, 3. Transparency, 4. Privacy and Security, 5. Reliability and Safety, and 6. Accountability

What are THREE Microsoft guiding principles for responsible AI? - Knowledge - Decisiveness - Inclusiveness - Fairness - Opinionatedness - Reliability and safety

- coefficient of determination (R2) - root mean squared error (RMSE) Notes: If the question is Regression model then remember "R" and the corresponding answer will be R2 and RMSE.

What are TWO metrics that you can use to evaluate a regression model? - coefficient of determination (R2) - F1 score - root mean squared error (RMSE) - area under curve (AUC) - balanced accuracy

- Detect brands in an image. - Detect the color scheme in an image.

What are TWO tasks that can be performed by using computer vision? - Predict stock prices. - Detect brands in an image. - Detect the color scheme in an image. - Translate text between languages. - Extract key phrases

- Detect faces in an image - Recognize handwritten text

What are TWO tasks that can be performed by using the Computer Vision service? - Train a custom image classification model. - Detect faces in an image. - Recognize handwritten text. - Translate the text in an image between languages.

- predicting whether someone uses a bicycle to travel to work based on the distance from home to work Notes: 1 would be regression. 2 would be clustering 3 is classification 4 would be regression

What is a use case for classification? - predicting how many cups of coffee a person will drink based on how many hours the person slept the previous night. - analyzing the contents of images and grouping images that have similar colors - predicting whether someone uses a bicycle to travel to work based on the distance from home to work - predicting how many minutes it will take someone to run a race based on past race times

to test the model by using data that was not used to train the model

When training a model, why should you randomly split the rows into separate subsets? - to train the model twice to attain better accuracy - to train multiple models simultaneously to attain better performance - to test the model by using data that was not used to train the model

transparency

When you design an AI system to assess whether loans should be approved, the factors used to make the decision should be explainable. This is an example of which Microsoft guiding principle for responsible AI? - transparency - inclusiveness - fairness - privacy and security

Describe the images

Which Computer Vision feature can you use to generate automatic captions for digital photographs? - Recognize text. - Identify the areas of interest. - Detect objects. - Describe the images.

- Combine multiple datasets. - Remove records that have missing values.

Which TWO actions are performed during the data ingestion and data preparation stage of an Azure Machine Learning process? - Calculate the accuracy of the model. - Score test data by using the model. - Combine multiple datasets. - Use the model for real-time predictions. - Remove records that have missing values

- Python - R

Which TWO languages can you use to write custom code for Azure Machine Learning designer? - Python - R - C# - Scala

true positive rate Notes: MAE, RMSE, and R2 are all metrics for regression.

Which metric can you use to evaluate a classification model? - true positive rate - mean absolute error (MAE) - coefficient of determination (R2) - root mean squared error (RMSE)

Form Recognizer

Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents? - Custom Vision - Face - Form Recognizer - Language

Form Recognizer

Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents? - Form Recognizer - Text Analytics - Language Understanding - Custom Vision

dataset module

Which two components can you drag onto a canvas in Azure Machine Learning designer? - dataset - compute - pipeline - module

regression Notes: Sales price is numeric, which makes the answer "regression".

Which type of machine learning should you use to identify groups of people who have similar purchasing habits? - classification - regression - clustering

regression

Which type of machine learning should you use to predict the number of gift cards that will be sold next month? - classification - regression - clustering

Enable Explain best model Note: Explain = Transparency

You 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? - Set Validation type to Auto. - Enable Explain best model. - Set Primary metric to accuracy. - Set Max concurrent iterations to 0.

- the trip distance of individual taxi journeys

You have a dataset that contains information about taxi journeys that occurred during a given period. You need to train a model to predict the fare of a taxi journey. What should you use as a feature? - the number of taxi journeys in the dataset - the trip distance of individual taxi journeys - the fare of individual taxi journeys - the trip ID of individual taxi journeys

Speech

You need to build an app that will read recipe instructions aloud to support users who have reduced vision. Which version service should you use? - Text Analytics - Translator - Speech - Language Understanding (LUIS)

Face

You need to build an image tagging solution for social media that tags images of your friends automatically. Which Azure Cognitive Services service should you use? - Face - Form Recognizer - Text Analytics - Computer Vision

Split Data

You need to create a training dataset and validation dataset from an existing dataset. Which module in the Azure Machine Learning designer should you use? - Select Columns in Dataset - Add Rows - Split Data - Join Data

Object detection Notes: object detection can identify location.

You need to determine the location of cars in an image so that you can estimate the distance between the cars. Which type of computer vision should you use? - optical character recognition (OCR) - object detection - image classification - face detection

Optical character recognition (OCR)

You need to develop a mobile app for employees to scan and store their expenses while travelling. Which type of computer vision should you use? - semantic segmentation - image classification - object detection - optical character recognition (OCR)

Regression Notes: Prediction of numeric values = regression

You need to predict the animal population of an area. Which Azure Machine Learning type should you use? - regression - clustering - classification

- Education Level - Age

You need to predict the income range of a given customer by using the following dataset: First Name Last Name Age Edu Level Income Range Orlando Gee 45 University 25,000-50,000 Keith Harris 36 High School 25,000-50,000 Donna Carreras 52 University 50,000-75,000 Janet Gates 21 University 75,000-100,000 Lucy Harrington 68 High school 50,000-75,000 Which TWO fields should you use as features? - Education Level - Last Name - Age - Income Range - First Name

- regression Notes: predicting numerical values without a yes or no is regression

You need to predict the sea level in meters for the next 10 years. Which type of machine learning should you use? - classification - regression - clustering

- Select Columns in dataset - Split Data - Linear Regression

You need to use Azure Machine Learning designer to build a model that will predict automobile prices. Which type of modules should you use to complete the model? CAN'T ADD BECAUSE OF PICTURE

Data preparation model training model evaluation

You plan to deploy an Azure Machine Learning model as a service that will be used by client applications. Which three processes should you perform in sequence before you deploy the model? Options Sequence - data encryption - model retraining - model training - data preparation - model evaluation

- QnA Maker - Azure Bot Service Notes: QnA has been replaced by "Azure Cognitive Language Service".

You plan to develop a bot that will enable users to query a knowledge base by using natural language processing. Which TWO services should you include in the solution? - QnA Maker - Azure Bot Service - Form Recognizer - Anomaly Detector

the Detect operation in the Face service

You run a charity event that involves posting photos of people wearing sunglasses on Twitter. You need to ensure that you only retweet photos that meet the following requirements: - Include one or more faces. - Contain at least one person wearing sunglasses. What should you use to analyze the images? - the Verify operation in the Face service - the Detect operation in the Face service - the Describe Image operation in the Computer Vision service - the Analyze Image operation in the Computer Vision service

object detection

You send an image to a Computer Vision API and receive back the annotated image shown in the exhibit. Banana (97.90%) Orange (96.77%) Apple (98.21%) Which type of computer vision was used? - object detection - face detection - optical character recognition (OCR) - image classification

- the authentication key - the REST endpoint

You use Azure Machine Learning designer to publish an inference pipeline. Which TWO parameters should you use to access the web service? - the model name - the training endpoint - the authentication key - the REST endpoint

Object detection Notes: Scene segmentation determines when a scene changes in a video based on visuals. A scene depicts a single event and it's composed by a series of consecutive shots, which are semantically related.

You use drones to identify where weeds grow between rows of crops to send an instruction for the removal of the weeds. This is an example of which type of computer vision? - object detection - optical character recognition (OCR) - scene segmentation

Computer Vision

Your company wants to build a recycling machine for bottles. The recycling machine must automatically identify bottles of the correct shape and reject all other items. Which type of AI workload should the company use? - anomaly detection - conversational AI - computer vision - natural language processing

natural language processing

Your website has a chatbot to assist customers. You need to detect when a customer is upset based on what the customer types in the chatbot. - anomaly detection - computer vision - regression - natural language processing

features

HOTSPOT Complete the sentence with the correct term. Data values that influence the prediction of a model are called ____________. - dependent variables - features - identifiers - labels

Azure Kubernetes Service (AKS).

HOTSPOT Complete the sentence with the correct term. From Azure Machine Learning designer, to deploy a real-time inference pipeline as a service for others to consume, you must deploy the model to ________________. - a local web service. - Azure Container Instances. - Azure Kubernetes Service (AKS). - Azure Machine Learning compute.

regression Notes: In the most basic sense, regression refers to prediction of a numeric target. Linear regression attempts to establish a linear relationship between one or more independent variables and a numeric outcome, or dependent variable. You use this module to define a linear regression method, and then train a model using a labeled dataset. The trained model can then be used to make predictions.

HOTSPOT Complete the sentence with the correct term. Predicting how many hours of overtime a delivery person will work based on the number of orders received is an example of _____________. - classification - clustering - regression

regression

HOTSPOT Complete the sentence with the correct term. Predicting how many vehicles will travel across a bridge on a given day is an example of __________. - classification - clustering - regression

Form Recognizer

HOTSPOT Complete the sentence with the correct term. The ability to extract subtotals and totals from a receipt is a capability of the ________ service. - Custom Vision - Form Recognizer - Ink Recognizer - Text Analytics

speech recognition

HOTSPOT Complete the sentence with the correct term. While presenting at a conference, your session is transcribed into subtitles for the audience. This is an example of ____________. - sentiment analysis - speech recognition - speech synthesis - translation

Confidence

HOTSPOT Complete the sentence with the correct term. ____________ is the calculated probability of a correct image classification. - Accuracy - Confidence - Root Mean Square Error - Sentiment

Custom Vision

HOTSPOT Complete the sentence with the correct term. ______________ service to train an object detection model by using your own images. - Computer Vision - Custom Vision - Form Recognizer - Video Indexer

- Object detection

HOTSPOT Complete the sentence. Returning a bounding box that indicates the location of a vehicle in an image is an example of ___________. - image classification. - object detection. - optical character recognizer (OCR). - semantic segmentation.

Yes No No

HOTSPOT For each of the following statements, select Yes if it is true. For a regression model, labels must be numeric. YES/NO For a clustering model, labels must be used. YES/NO For a classification model, labels must be numeric. YES/NO

No Yes Yes Notes: 1 - Object detection has no further types to choose from.

HOTSPOT For each of the following statements, select Yes if it is true. When creating an object detection model in the Custom Vision service, you must choose a classification type of either Multilabel or Multiclass. YES/NO You can create an object detection model in the Custom Vision service to find the location content within an image. YES/NO When creating an object detection model in the Custom Vision service, you can select from a set of predefined domains. YES/NO

No No Yes

HOTSPOT For each of the following statements, select Yes if it is true. You train a regression model by using unlabeled data. YES/NO The classification technique is used to predict sequential numerical data over time. YES/NO Grouping items by their common characteristics is an example of clustering. YES/NO

a reduced workload for the customer service agents

A company employs a team of customer service agents to provide telephone and email support to customers. The company develops a webchat bot to provide automated answers to common customer queries. Which business benefit should the company expect as a result of creating the webchat bot solution? - increased sales - a reduced workload for the customer service agents - improved product reliability

classification

A medical research project uses a large anonymized dataset of brain scan images that are categorized into predefined brain hemorrhage types. You need to use machine learning to support early detection of the different brain hemorrhage types in the images before the images are reviewed by a person. This is an example of which type of machine learning? - clustering - regression - classification

classification

HOTSPOT Complete each sentence with the correct term. A banking system that predicts whether a loan will be repaid is an example of the _________ type of machine learning. - classification - regression - clustering

reliability and safety

HOTSPOT Complete the following sentence: The handling of unusual or missing values provided to an AI system is a consideration for the Microsoft _________________ Principle for responsible AI. - inclusiveness - privacy and security - reliability and safety - transparency

Feature engineering

HOTSPOT Complete the sentence _______ is used to generate additional features. - Feature engineering - Feature selection - Model evaluation - Model training

- adding and connecting modules on a visual canvas.

HOTSPOT Complete the sentence with the correct statement. Azure Machine Learning designer lets you create machine learning models by ______________________. - adding and connecting modules on a visual canvas. - automatically performing common data preparation tasks. - automatically selecting an algorithm to build the most accurate model. - using a code-first notebook experience.

Fairness

HOTSPOT Complete the sentence with the correct term. According to Microsoft's _________ principle of responsible AI, AI systems should NOT reflect biases from the data sets that are used to train the systems. - accountability - fairness - inclusiveness - transparency

Computer vision Notes: Counting the number of animals based on a video feed is an example of an AI service called object detection, which is a type of computer vision technology.

HOTSPOT Complete the sentence with the correct term. Counting the number of animals in an area based on a video feed is an example of ____________. - forecasting. - computer vision. - conversational AI. - anomaly detection.

- providing closed captions for recorded or live videos - creating a transcript of a telephone call or meeting

In which TWO scenarios can you use speech recognition? - an in-car system that reads text messages aloud - providing closed captions for recorded or live videos - creating an automated public address system for a train station - creating a transcript of a telephone call or meeting

- Extract the invoice number from an invoice. - Identify the retailer from a receipt.

In which TWO scenarios can you use the Form Recognizer service? - Extract the invoice number from an invoice. - Translate a form from French to English - Find image of product in a catalog. - Identify the retailer from a receipt.

- Identify the retailer from a receipt. - Extract the invoice number from an invoice

In which TWO scenarios can you use the Form Recognizer service? - Identify the retailer from a receipt. - Translate from French to English. - Extract the invoice number from an invoice. - Find images of products in a catalog

Image classification Object detection Semantic segmentation Notes: 1 : Image classification 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. 2 : Object detection is a computer vision problem. While closely related to image classification, object detection performs image classification at a more granular scale. Object detection both locates and categorizes entities within images. 3 : Semantic segmentation achieves fine-grained inference by making dense predictions inferring labels for every pixel, so that each pixel is labelled with the class of its enclosing object or region.

Match the types of machine learning to the appropriate scenarios. Each answer Statement _________ : Separate images of polar bears and brown bears. __________: Determine the location of a bear in a photo. __________: Determine which pixels in an image are part of a bear. Answer Area - Facial Detection - Facial recognition - Image classification - Object detection - Optical character recognition (OCR) - Semantic segmentation

Reliability and safety Accountability Privacy and security

Principles Accountability Fairness Inclusiveness Privacy and security Reliability and safety Answer Area Ensure that AI systems operate as they were originally designed, respond to unanticipated conditions, and resist harmful manipulation. (Principal type?) Implementing processes to ensure that decisions made by AI systems can be overridden by humans. (Principle type?) Provide consumers with information and controls over the collection, use, and storage of their data. (Principle type?)

Conversational AI Computer Vision Natural Language Processing (NLP)

Workload Types Anomaly Detection Computer Vision Conversational AI Knowledge mining Natural Language Processing ANSWER AREA An automated chat to answer questions about refunds and exchange. (Workload type?) Determining whether a photo contains a person. (Workload type?) Determining whether a review is positive or negative? (Workload type?)

Custom Vision

You are building a tool that will process images from retail stores and identify the products of competitors. The solution will use a custom model. Which Azure Cognitive Services service should you use? - Custom Vision - Form Recognizer - Face - Computer Vision

Provide documentation to help developers debug code.

You are building an AI system. Which task should you include to ensure that the service meets the Microsoft transparency principle for responsible AI? - Ensure that all visuals have an associated text that can be read by a screen reader. - Enable autoscaling to ensure that a service scales based on demand. - Provide documentation to help developers debug code. - Ensure that a training dataset is representative of the population

- Implement a process of AI model validation as part of the software review process - Establish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer

You are building an AI-based app. You need to ensure that the app uses the principles for responsible AI. Which two principles should you follow? - Implement an Agile software development methodology - Implement a process of AI model validation as part of the software review process - Establish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer - Prevent the disclosure of the use of AI-based algorithms for automated decision making.

inclusiveness

You are designing an AI system that empowers everyone, including people who have hearing, visual, and other impairments. This is an example of which Microsoft guiding principle for responsible AI? - fairness - inclusiveness - accountability

key phrase extraction

You are developing a solution that uses the Text Analytics service. You need to identify the main talking points in a collection of documents. Which type of natural language processing should you use? - entity recognition - key phrase extraction - sentiment analysis - language detection

- Use a graphical user interface (GUI) to run automated machine learning experiments - Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer

You are evaluating whether to use a basic workspace or an enterprise workspace in Azure Machine Learning. What are TWO tasks that require an enterprise workspace? - Use a graphical user interface (GUI) to run automated machine learning experiments - Create a compute instance to use as a workstation - Use a graphical user interface (GUI) to define and run machine learning experiments from Azure Machine Learning designer - Create a dataset from a comma-separated value (CSV) file.

Optical character recognition (OCR)

You are processing photos of runners in a race. You need to read the numbers on the runners' shirts to identify the runners in photos. Which type of computer vision should you use? - facial recognition - optical character recognition (OCR) - image classification - object detection