(March 2024) AI-900 Practice Questions

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? To answer, move the appropriate processes from the list of processes to the answer area and arrange them in the correct order. Data Encryption Model Retraining Model Training Data Preparation Model Valuation

(1) Data Preparation (2) Model Training (3) Model Evaluation

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Automated machine learning provides you with the ability to include custom Python scripts in a training pipeline 2) Automated machine learning implements machine learning solutions without the need for programming experience 3) Automated machine learning provides you with the ability to visually connect datasets and modules on an interactive canvas

A) No B) Yes C) No Explanation: A) In Automated ML , you cannot insert Python code. C) in Automated ML, though you can select Data but not modules... No Canvas is used in Auto ML.

A banking system that predicts whether a loan will be repaid is an example of the ________________ type of machine learning A) classification B) regression C) clustering

A) classification Explanation: Two-class classification provides the answer to simple two-choice questions such as Yes/No or True/False.

What are two metrics that you can use to evaluate a regression model? Each correct answer presents a complete solution.NOTE: Each correct selection is worth one point. A. coefficient of determination (R2) B. F1 score C. root mean squared error (RMSE) D. area under curve (AUC) E. balanced accuracy

A. coefficient of determination (R2) C. root mean squared error (RMSE) Explanation: A: R-squared (R2), or Coefficient of determination represents the predictive power of the model as a value between -inf and 1.00. 1.00 means there is a perfect fit, and the fit can be arbitrarily poor so the scores can be negative. B: F1 score also known as balanced F-score or F-measure is used to evaluate a classification model. C: RMS-loss or Root Mean Squared Error (RMSE) (also called Root Mean Square Deviation, RMSD), measures the difference between values predicted by a model and the values observed from the environment that is being modeled. D: ROC or area under the curve (AUC) is used to evaluate a classification model.

Which two components can you drag onto a canvas in Azure Machine Learning designer? Each correct answer presents a complete solution.NOTE: Each correct selection is worth one point. A. dataset B. compute C. pipeline D. module

A. dataset D. module Explanation: Azure Machine Learning designer lets you visually connect datasets and modules on an interactive canvas to create machine learning models. A "module" refers to an individual operation or step that you can add to your machine learning workflow. These modules represent specific tasks or operations, such as data preprocessing, feature engineering, model training, model scoring, and evaluation.

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

A. true positive rate Explanation: An ROC curve that approaches the top left corner with 100% true positive rate and 0% false positive rate will be the best model. A random model would display as a flat line from the bottom left to the top right corner. Worse than random would dip below the y=x line.

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? Each module may be used once, more than once, or not at all Modules: - Convert to CSV - K-Means Clustering - Linear Regression - Split Data - Select Columns in Dataset - Summarize Data Automobile Price Data (Raw) ↓ [Answer Choice 1] ↓ Clean Missing Data ↓ [Answer Choice 2] → Score Model ↓ Train Model ← [Answer Choice 3] ↓ Score Model

Automobile Price Data (Raw) ↓ SELECT COLUMNS IN DATASET ↓ Clean Missing Data ↓ SPLIT DATA → Score Model ↓ Train Model ← LINEAR REGRESSION ↓ Score Model ** SPLIT DATA REFERS TO CREATING TRAINING/VALIDATION SETS

___________________________ is the calculated probability of a correct image classification A) Accuracy B) Confidence C) Root Mean Square Error D) Sentiment

B) Confidence

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? A) Set validation type to Auto B) Enable Explain best model C) Set Primary metric to accuracy D) Set Max concurrent iterations to 0

B) Enable Explain best model Explanation: MS AI responsibilities • Fairness - Limit Biases • Reliability ad Safely - ops, resist manipulating, use of regresses testing • Privacy and security- secure data provide security controls • Inclusiveness- AI available to everyone i.e., disabled ppl • Transparency- fully aware of the limitations over AII in use • Accountability- follow governments and frameworks meet legal and ethical standards

According to Microsoft's __________________ principle of AI, AI systems should NOT reflect biases from the data sets that are used to train the systems A) Accountability B) Fairness C) Inclusiveness D) Transparency

B) Fairness

The ability to extract subtotals and totals from a receipt is a capability of the ______________ service A) Custom Vision B) Form Recognizer / Azure AI Document Intelligence C) Ink Recognizer D) Text Analytics

B) Form Recognizer / Azure AI Document Intelligence Explanation: Accelerate your business processes by automating information extraction. Form Recognizer applies advanced machine learning to accurately extract text, key/ value pairs, and tables from documents. With just a few samples, Form Recognizer tailors its understanding to your documents, both on-premises and in the cloud. Turn forms into usable data at a fraction of the time and cost, so you can focus more time acting on the information rather than compiling it.

Data values that influence the prediction of a model are called _______________________________ A) dependent variables B) features C) identifiers D) labels

B) features

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

B. Randomly split the data into rows for training and rows for evaluation Explanation: The Split Data module is particularly useful when you need to separate data into training and testing sets. Use the Split Rows option if you want to divide the data into two parts. You can specify the percentage of data to put in each split, but by default, the data is divided 50-50. You can also randomize the selection of rows in each group, and use stratified sampling.

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? A. increased sales B. a reduced workload for the customer service agents C. improved product reliability

B. a reduced workload for the customer service agents

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? A. the Verify operation in the Face service B. the Detect operation in the Face service C. the Describe Image operation in the Computer Vision service D. the Analyze Image operation in the Computer Vision service

B. the Detect operation in the Face service Explanation: Face detection can extract a set of face-related attributes, such as head pose, age, emotion, facial hair, and glasses

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

C. Provide documentation to help developers debug code.

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? A. Select Columns in Dataset B. Add Rows C. Split Data D. Join Data

C. Split Data Explanation: A common way of evaluating a model is to divide the data into a training and test set by using Split Data, and then validate the model on the training data.Use the Split Data module to divide a dataset into two distinct sets.

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

C. clustering

What are three Microsoft guiding principles for responsible AI? Each correct answer presents a complete solution. A. knowledgeability B. decisiveness C. inclusiveness D. fairness E. opinionatedness F. reliability and safety

C. inclusiveness D. fairness F. reliability and safety

Match the types of AI workloads to the appropriate scenarios. To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all. Workload Types: - Anomaly detection - Computer vision - Machine Learning (Regression) - Natural language processing 1) _______________________________________ - identify handwritten letters 2) _______________________________________ - predict the sentiment of a social media post 3) _______________________________________ - identify a fraudulent credit card payment 4) _______________________________________ - predict next month's toy sales

1) Computer vision - identify handwritten letters 2) Natural language processing - predict the sentiment of a social media post 3) Anomaly detection - identify a fraudulent credit card payment 4) Machine Learning (Regression) - predict next month's toy sales

Match the types of AI workloads to the appropriate scenarios.To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all. Workload Types: - Anomaly detection - Computer Vision - Conversational AI - Knowledge Mining - Natural language processes 1) ____________________________________________________ - an automated chatbot to answer questions about refunds and exchange 2) ___________________________________________________ - determining whether a photo contains a person 3) ___________________________________________________ - determining whether a review is positive or negative

1) Conversational AI - an automated chat to answer questions about refunds and exchange 2) Computer vision - determining whether a photo contains a person 3) Natural language processing - determining whether a review is positive or negative Explanation: The Computer Vision Image Analysis service can extract a wide variety of visual features from your images. For example, it can determine whether an image contains adult content, find specific brands or objects, or find human faces. Natural language processing (NLP) is used for tasks such as sentiment analysis, topic detection, language detection, key phrase extraction, and document categorization

Match the principles of responsible AI to appropriate requirements. To answer, drag the appropriate principles from the column on the left to its requirement on the right. Each principle may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content. Principles: - Fairness - Privacy and Security - Reliability and safety - Transparency 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

1) Fairness - the system must not discriminate based on gender, race 2) Privacy and Security - personal data must be visible only to approve 3) Transparency - automated decision-making processes must be recorded so that approved users can identify why a decision was made

You have the following dataset: Household Income: 20,000 23,000 80,000 Postal Code: 55555 20541 87960 House Price Category: Low Middle High You plan to use the dataset to train a model that will predict the house price categories of houses. What are Household Income and House Price Category? 1) Household Income is a _____________________ A) Feature B) Label 2) House Price Category is a ______________________ A) Feature B) Label

1) Household Income is a feature Household Income is being used to predict the house price category 2) House Price Category is a label House Price Category is the dependent variable or what the model is predicting and is therefore the label

Match the types of AI workloads to the appropriate scenarios.To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all. Learning Types: - Feature engineering - Feature selection - Model deployment - Model evaluation - Model training 1) ___________________________________ - examining the values of a confusion matrix 2) ___________________________________ - splitting a date into month, day, and year fields 3) ___________________________________ - picking temperature and pressure to train a weather model

1) Model evaluation - examining the values of a confusion matrix The Model evaluation module outputs a confusion matrix showing the number of true positives, false negatives, false positives, and true negatives, as well as ROC, Precision/Recall, and Lift curves. 2) Feature engineering - splitting a date into month, day, and year fields Feature engineering is the process of using domain knowledge of the data to create features that help ML algorithms learn better. In Azure Machine Learning, scaling and normalization techniques are applied to facilitate feature engineering. Collectively, these techniques and feature engineering are referred to as featurization. Note: Often, features are created from raw data through a process of feature engineering. For example, a time stamp in itself might not be useful for modeling until the information is transformed into units of days, months, or categories that are relevant to the problem, such as holiday versus working day. 3) Feature selection - picking temperature and pressure to train a weather model In machine learning and statistics, feature selection is the process of selecting a subset of relevant, useful features to use in building an analytical model. Feature selection helps narrow the field of data to the most valuable inputs. Narrowing the field of data helps reduce noise and improve training performance.

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) A validation set includes the set of input examples that will be used to train a model 2) A validation set can be used to determine how well a model predicts labels 3) A validation set can be used to verify that all the training data was used to train the model

1) No 2) Yes 3) No

Match the types of machine learning to the appropriate scenarios. Each machine learning type may be used once, more than once, or not at all. Learning Types: - Classification - Clustering - Regression 1) _______________________________________________ - predict how many minutes late a flight will arrive based on the amount of snowfall at an airport 2) _______________________________________________ - segment customers into different groups to support a marketing department 3) _______________________________________________ - predict whether a student will complete a university course

1) Regression - predict how many minutes late a flight will arrive based on the amount of snowfall at an airport 2) Clustering - segment customers into different groups to support a marketing department 3) Classification - predict whether a student will complete a university course

Match the Microsoft guiding principles for responsible AI to the appropriate descriptions. To answer, drag the appropriate principle from the column on the left to its description on the right. Each principle may be used once, more than once, or not at all. Principles: - Accountability - Fairness - Inclusiveness - Privacy & Security - Reliability and Safety 1) ___________________________________________ - ensure that AI systems operate as they were originally designed, respond to unanticipated conditions, and resist harmful manipulation 2) ___________________________________________ - implementing processes to ensure that decisions made by AI systems can be overridden by humans 3) ___________________________________________ - provide consumers with information and controls over the collective, use, and storage of their data

1) Reliability and Safety - ensure that AI systems operate as they were originally designed, respond to unanticipated conditions, and resist harmful manipulation 2) Accountability - implementing processes to ensure that decisions made by AI systems can be overridden by humans 3) Privacy and security - provide consumers with information and controls over the collective, use, and storage of their data

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Azure Machine Learning designer provides a drag and drop visual canvas to build, test, and deploy machine learning models 2) Azure Machine Learning designer enables you to save your progress as a pipeline draft 3) Azure Machine Learning designer enables you to include custom JavaScript functions

1) Yes 2) Yes 3) No You can customize only using Python and R code.

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Organizing documents into groups based on similarities of the text contained in the documents is an example of clustering 2) Grouping similar patients based on symptoms and diagnostic test results is an example of clustering 3) Predicting whether a person will develop mild, moderate, or severe allergy symptoms based on pollen count is an example of clustering

1) Yes 2) Yes 3) No Explanation: Clustering is a machine learning task that is used to group instances of data into clusters that contain similar characteristics. Clustering can also be used to identify relationships in a dataset. Regression is a machine learning task that is used to predict the value of the label from a set of related features.

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Automated machine learning is the process of automating the time-consuming, iterative tasks of ML model development 2) AUtomated machine learning can automatically infer the training data from the use case provided 3) Automated machine learning works by running multiple training iterations that are scored and ranked by the metrics you specify 4) Automated machine learning enables you to specify a dataset and will automatically understand which label to predict

1) Yes Automated machine learning, also referred to as automated ML or AutoML, is the process of automating the time consuming, iterative tasks of machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and productivity all while sustaining model quality 2) No 3) Yes During training, Azure Machine Learning creates a number of pipelines in parallel that try different algorithms and parameters for you. The service iterates throughML algorithms paired with feature selections, where each iteration produces a model with a training score. The higher the score, the better the model is considered to "fit" your data. It will stop once it hits the exit criteria defined in the experiment. 4) No

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Labelling is the process of tagging training data with known values 2) You should evaluate a model by using the same data used to train the model 3) Accuracy is always the primary metric used to measure a model's performance

1) Yes Data labeling (also known as data annotation or tagging) is indeed the process of adding tags or labels to raw data such as images, videos, text, and audio. These labels provide context and meaning to the data, enabling machine learning algorithms to learn and make predictions based on the annotated information. 2) No 3) No Accuracy is simply the proportion of correctly classified instances. It is usually the first metric you look at when evaluating a classifier. 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 classifier.

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1) Providing an explanation of the outcome of a credit loan application is an example of the Microsoft transparency principle for responsible AI 2) A triage bot that prioritizes insurance claims based on injuries is an example of the Microsoft reliability and safety principle for responsible AI 3) An AI solution that is offered at different prices for different sales territories is an example of the Microsoft inclusiveness principle for responsible AI

1) Yes - 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 final 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. 2) No - it should be related to "privacy and security" 3) No - Inclusiveness is more about avoiding bias, discrimination, and ensuring that AI benefits all individuals and groups fairly. Different pricing for different territories may raise concerns about fairness, but it doesn't directly relate to inclusiveness.

For each of the following statements, select Yes if the statement is true. Otherwise, select No. 1. Forecasting housing prices based on historical data is an example of anomaly detection (Yes/No) 2. Identifying suspicious sign ins by looking for deviations from usual patterns is an example of anomaly detection (Yes/No) 3. Predicting whether a patient will develop diabetes based on the patient's medical history is an example of anomaly detection (Yes/No)

1. No 2. Yes 3. No Explanation: Anomaly detection encompasses many important tasks in machine learning: - Identifying transactions that are potentially fraudulent. - Learning patterns that indicate that a network intrusion has occurred. - Finding abnormal clusters of patients. - Checking values entered into a system.

Azure Machine Learning designers lets you create machine learning modules by ___________________________ A) adding and connecting modules on a visual canvas B) automatically performing common data preparation tasks C) automatically selecting an algorithm to build the most accurate model D) using a code-first notebook experience

A) adding and connecting modules on a visual canvas Explanation: Azure Machine Learning designer is a drag-and-drop UI interface for building machine learning pipelines in Azure Machine Learning Workspaces. You can build a pipeline visually by dragging and dropping building blocks and connecting them.

_________________ is used to generate additional features A) feature engineering B) feature selection C) model evaluation D) model training

A) feature engineering Explanation: Feature engineering is applied first to generate additional features, and then feature selection is done to eliminate irrelevant, redundant, or highly correlated features.

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? A. Custom Vision B. Form Recognizer / Document Intelligence C. Face D. Computer Vision

A. Custom Vision Explanation: Azure Custom Vision is an image recognition service that lets you build, deploy, and improve your own image identifier models. An image identifier applies labels (which represent classifications or objects) to images, according to their detected visual characteristics. Unlike the Computer Vision service, Custom Vision allows you to specify your own labels and train custom models to detect them. Custom model = Custom Vision

You need to predict the income range of a given customer by using the following dataset columns: - First Name - Last Name - Age - Education Level - Income Range Which two fields should you use as features? A. Education Level B. Last Name C. Age D. Income Range E. First Name

A. Education Level C. Age Explanation: First Name, Last Name, Age and Education Level are features. Income range is a label (what you want to predict). First Name and Last Name are irrelevant in that they have no bearing on income. Age and Education level are the features you should use.

Which service should you use to extract text, key/value pairs, and table data automatically from scanned documents? A. Form Recognizer / Azure AI Document Intelligence B. Text Analytics C. Language Understanding D. Custom Vision

A. Form Recognizer / Azure AI Document Intelligence Explanation: Table, receipts, invoice --> Azure AI Document Intelligence

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? A. transparency B. inclusiveness C. fairness D. privacy and security

A. transparency Explanation: 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 final 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. B: 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. C: Fairness is a core ethical principle that all humans aim to understand and apply. This principle is even more important when AI systems are being developed.Key checks and balances need to make sure that the system's decisions don't discriminate or run a gender, race, sexual orientation, or religion bias toward a group or individual. D: 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.

You need to predict the sea level in meters for the next 10 years.Which type of machine learning should you use? A) Classification B) Regression C) Clustering

B) Regression Explanation: 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.

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? A) fairness B) inclusiveness C) reliability and safety D) accountability

B) inclusiveness

Returning a bounding box that indicates the location of a vehicle in an image is an example of ______________________________ A) image classification B) object detection C) optical character recognizer (OCR) D) semantic segmentation

B) object detection

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

B) regression Explanation: 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.

You use Azure Machine Learning designer to publish an inference pipeline. Which two parameters should you use to access the web service? A) the model name B) the training endpoint C) the authentication key D) the REST endpoint

C) the authentication key D) the REST endpoint Explanation: Since the service is exposed as a REST API, you need a REST endpoint and an API key to authenticate requests.

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? A. Implement an Agile software development methodology B. Implement a process of AI model validation as part of the software review process C. Establish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer D. Prevent the disclosure of the use of AI-based algorithms for automated decision making

B. Implement a process of AI model validation as part of the software review process C. Establish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer Explanation: B ensures reliability and safety principle and C ensures privacy and security principle of AI.

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? A. the number of taxi journeys in the dataset B. the trip distance of individual taxi journeys C. the fare of individual taxi journeys D. the trip ID of individual taxi journeys

B. the trip distance of individual taxi journeys Explanation: The label is the column you want to predict. The identified Features are the inputs you give the model to predict the Label.

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) a local web service B) Azure Container Instances C) Azure Kubernetes Service (AKS) D) Azure Machine Learning compute

C) Azure Kubernetes Service (AKS) Explanation: To perform real-time inferencing, you must deploy a pipeline as a real-time endpoint. The real-time endpoint creates an interface between an external application and your scoring model. A call to a real-time endpoint returns prediction results to the application in real-time. To make a call to a real-time endpoint, you pass the API key that was created when you deployed the endpoint. The endpoint is based on REST, a popular architecture choice for web programming projects. Real-time endpoints must be deployed to an Azure Kubernetes Service cluster.

Predicting how many hours of overtime a delivery person will work based on the number of order received is an example of ______________________ A) Classification B) Clustering C) Regression

C) Regression

______________ models can be used to predict the sale price of auctioned items A) Classification B) Clustering C) Regression

C) Regression

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

C) classification

__________________________________________ used to extract dates, quantities, and locations from text A) key phrase extraction B) language detection C) named entity recognition (NER) D) sentiment analysis

C) named entity recognition (NER)

Predicting how many vehicles will travel across a bridge on a given day is an example of ____________________________ A) classification B) clustering C) regression

C) regression

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 A) inclusiveness B) accountability C) reliability and safety D) fairness

C) reliability and safety

The handling of unusual or missing values provided to an AI system is a consideration for the Microsoft _____________ principle for responsible AI A) inclusiveness B) privacy and security C) reliability and safety D) transparency

C) reliability and safety Explanation: AI systems need to be reliable and safe in order to be trusted. It is important for a system to perform as it was originally designed and for it to respond safely to new situations. Its inherent resilience should resist intended or unintended manipulation. Rigorous testing and validation should be established for operating conditions to ensure that the system responds safely to edge cases, and A/B testing and champion/challenger methods should be integrated into the evaluation process. An AI system's performance can degrade over time, so a robust monitoring and model tracking process needs to be established to reactively and proactively measure the model's performance and retrain it, as necessary, to modernize it.

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

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

You are developing a model to predict events by using classification.You have a confusion matrix for the model scored on test data as shown in the following exhibit. Predicted: 1 | Actual: 1 = 11 Predicted: 1 | Actual: 0 = 5 Predicted: 0 | Actual: 1 = 1033 Predicted: 0 | Actual: 0 = 13951 There are _____________________ correctly predicted positives There are _____________________ false negatives

There are 11 correctly predicted positives There are 1033 false negatives