AI-900 practice questions 61–70

1. Question 61 · 236 in bank

   You have a natural language processing (NLP) model that was created by using data obtained without permission. Which Microsoft principle for responsible AI does this breach?

   • Areliability and safety
   • Bprivacy and security
   • Cinclusiveness
   • Dtransparency

   Show answer

   Answer: B

   Explanation

   In this case, creating an NLP model using data obtained without permission breaches the principle of **privacy and security**. Source: Conversation with Bing, 4/26/2023 (1) Responsible and trusted AI - Cloud Adoption Framework | Microsoft Learn. https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/innovate/best-practices/trusted-ai Accessed 4/26/2023. (2) Responsible AI principles from Microsoft. https://www.microsoft.com/en-us/ai/responsible-ai Accessed 4/26/2023. (3) Responsible AI principles from Microsoft. https://www.microsoft.com/en-gb/ai/responsible-ai Accessed 4/26/2023. (4) Identify guiding principles for responsible AI - Training. https://learn.microsoft.com/en-us/training/modules/responsible-ai-principles/ Accessed 4/26/2023. (5) Responsible AI - Cloud Adoption Framework | Microsoft Learn. https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/strategy/responsible-ai Accessed 4/26/2023.

   Source: Adapted from community discussion — master_yoda

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Next question

2. Question 62 · 236 in bank

   HOTSPOT - Select the answer that correctly completes the sentence.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   References

   • Microsoft Learn

   

   Next question

3. Question 63 · 236 in bank

   DRAG DROP - Match the services to the appropriate descriptions. To answer, drag the appropriate service from the column on the left to its description on the right. Each service 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. NOTE: Each correct selection is worth one point.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   1. Language Service 2. Speech https://learn.microsoft.com/en-us/training/modules/build-faq-chatbot-qna-maker-azure-bot-service/2-get-started-knowledge-base The Language service includes a custom question answering feature that enables you to create a knowledge base of question and answer pairs that can be queried using natural language input. https://learn.microsoft.com/en-us/azure/cognitive-services/speech-service/overview The Speech service provides speech to text and text to speech capabilities with an Speech resource. You can transcribe speech to text with high accuracy, produce natural-sounding text to speech voices, translate spoken audio, and use speaker recognition during conversations.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

4. Question 64 · 236 in bank

   Which machine learning technique can be used for anomaly detection?

   • AA machine learning technique that classifies objects based on user supplied images.
   • BA machine learning technique that understands written and spoken language.
   • CA machine learning technique that classifies images based on their contents.
   • DA machine learning technique that analyzes data over time and identifies unusual changes.

   Show answer

   Answer: D

   Explanation

   D is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/overview Anomaly Detector is an AI service with a set of APIs, which enables you to monitor and detect anomalies in your time series data with little machine learning (ML) knowledge, either batch validation or real-time inference.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn

   Next question

5. Question 65 · 236 in bank

   HOTSPOT - To complete the sentence, select the appropriate option in the answer area. Hot Area:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   Reference: https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/create-features

   Source: Adapted from community discussion — swapmaverick

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

6. Question 66 · 236 in bank

   You have an AI-based loan approval system. During testing, you discover that the system has a gender bias. Which responsible Al principle does this violate?

   • Aaccountability
   • Breliability and safety
   • Ctransparency
   • Dfairness

   Show answer

   Answer: D

   References

   • Microsoft Learn

   Next question

7. Question 67 · 236 in bank

   You are developing a system to predict the prices of insurance for drivers in the United Kingdom. You need to minimize bias in the system. What should you do?

   • ARemove information about protected characteristics from the data before sampling.
   • BTake a training sample that is representative of the population in the United Kingdom.
   • CCreate a training dataset that uses data from global insurers.
   • DTake a completely random training sample.

   Show answer

   Answer: B

   Explanation

   B. Take a training sample that is representative of the population in the United Kingdom. To minimize bias in the system, it's important that your training data is representative of the population you're modeling. This helps ensure that the model's predictions are valid for the full range of drivers in the United Kingdom. While option A (Remove information about protected characteristics from the data before sampling) could help in some cases to reduce direct discrimination, it might not be sufficient to minimize all types of biases, as some of these characteristics might be indirectly encoded in the remaining features. Option C (Create a training dataset that uses data from global insurers) may introduce more bias since driving conditions, laws, and demographics vary greatly by country. Option D (Take a completely random training sample) could still introduce bias if the original data pool is not representative of the population you're interested in.

   Source: Adapted from community discussion — redsoxfred

   Next question

8. Question 68 · 236 in bank

   HOTSPOT - Select the answer that correctly completes the sentence.

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   1. adding and connecting modules on a visual canvas https://learn.microsoft.com/en-us/azure/machine-learning/concept-designer?view=azureml-api-2 Azure Machine Learning designer is a drag-and-drop UI interface to build pipeline in Azure Machine Learning.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn

   

   Next question

9. Question 69 · 236 in bank

   You have a dataset. You need to build an Azure Machine Learning classification model that will identify defective products. What should you do first?

   • ALoad the dataset.
   • BCreate a clustering model.
   • CSplit the data into training and testing datasets.
   • DCreate a classification model.

   Show answer

   Answer: A

   Explanation

   A is the answer. https://learn.microsoft.com/en-us/training/modules/create-classification-model-azure-machine-learning-designer/classification-steps You can think of the steps to train and evaluate a classification machine learning model as: - Prepare data: Identify the features and label in a dataset. Pre-process, or clean and transform, the data as needed. - Train model: Split the data into two groups, a training and a validation set. Train a machine learning model using the training data set. Test the machine learning model for performance using the validation data set. - Evaluate performance: Compare how close the model's predictions are to the known labels. - Deploy a predictive service: After you train a machine learning model, you need to convert the training pipeline into a real-time inference pipeline. Then you can deploy the model as an application on a server or device so that others can use it.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn

   Next question

10. Question 70 · 236 in bank

    You use Azure Machine Learning designer to build a model pipeline. What should you create before you can run the pipeline?

    • Aa registered model
    • Ba compute resource
    • Ca Jupyter notebook

    Show answer

    Answer: B

    References

    • Microsoft Learn

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AI-900 practice, question 61. 236 questions available.