AI-900 practice questions 131–140

1. Question 131 · 236 in bank

   Select 2

   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? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

   • AImplement an Agile software development methodology
   • BImplement a process of AI model validation as part of the software review process
   • CEstablish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer
   • DPrevent the disclosure of the use of AI-based algorithms for automated decision making

   Show answer

   Answer: BC

   Explanation

   BC is the answer. https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/innovate/best-practices/trusted-ai#reliability-and-safety AI systems need to be reliable and safe in order to be trusted. It's 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.

   Source: Adapted from community discussion — zellck

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   Next question

2. Question 132 · 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

   I think the answer is text extraction Since the goal is to extract the vehicle registration numbers from the CCTV footage, text extraction using OCR algorithms would be the most appropriate choice. OCR algorithms can recognize and extract text information from images, making it possible to retrieve the registration numbers from the captured video frames. This enables automated monitoring and analysis of the traffic data by extracting the relevant textual information.

   Source: Adapted from community discussion — redsoxfred

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

3. Question 133 · 236 in bank

   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?

   • AFace
   • BForm Recognizer
   • CLanguage
   • DComputer Vision

   Show answer

   Answer: A

   Explanation

   Face: While Face can detect faces, it wouldn't be suitable for tagging general objects or scenes in social media images that might not contain people. Therefore, D - Computer Vision

   Source: Adapted from community discussion — gvldesigner

   Next question

4. Question 134 · 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

   

   Next question

5. Question 135 · 236 in bank

   HOTSPOT - You have an app that identifies birds in images. The app performs the following tasks: • Identifies the location of the birds in the image • Identifies the species of the birds in the image Which type of computer vision does each task use? To answer, select the appropriate options in the answer area. 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

   Think the answers are correct, but using a Custom Vision Image Classification Model, you would be able to use Obejct Detection as well (assuming it is trained on the species of bird)

   Source: Adapted from community discussion — Moppu

   

   Next question

6. Question 136 · 236 in bank

   You have a solution that reads manuscripts in different languages and categorizes the manuscripts based on topic. Which types of natural language processing (NLP) workloads does the solution use?

   • Aspeech recognition and entity recognition
   • Bspeech recognition and language modeling
   • Ctranslation and key phrase extraction
   • Dtranslation and sentiment analysis

   Show answer

   Answer: C

   Explanation

   Here is the answer quoted from MS Copilot: "The solution you described involves reading manuscripts in different languages and categorizing them based on topic. This would primarily involve: 1. Translation: To convert the content of the manuscripts from various languages to a language the model can understand. 2. Key Phrase Extraction: To identify and extract the main topics or themes from the manuscript content. So, the correct answer is C. translation and key phrase extraction. Please note that depending on the specific requirements of the solution, other NLP tasks could also be relevant. For example, entity recognition could be used to identify specific entities within the text, and sentiment analysis could be used to understand the tone or sentiment of the manuscript. However, based on the information provided, translation and key phrase extraction are the most directly relevant tasks."

   Source: Adapted from community discussion — rafcio1990

   Next question

7. Question 137 · 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

   

   Next question

8. Question 138 · 236 in bank

   You have 100 instructional videos that do NOT contain any audio. Each instructional video has a script. You need to generate a narration audio file for each video based on the script. Which type of workload should you use?

   • Alanguage modeling
   • Bspeech recognition
   • Cspeech synthesis
   • Dtranslation

   Show answer

   Answer: C

   References

   • Microsoft Learn

   Next question

9. Question 139 · 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

   

   Next question

10. Question 140 · 236 in bank

    Which AI service can you use to extract intent from a user input such as “Call me back later”?

    • AAzure Cognitive Search
    • BTranslator
    • CLanguage
    • DSpeech

    Show answer

    Answer: C

    Explanation

    C. Language You can use the Azure Cognitive Services Language service to extract intent from a user input like "Call me back later." This service provides natural language processing (NLP) capabilities, including intent recognition, and can be used to understand the meaning and intent behind user text input. It's commonly used for tasks like chatbots, virtual assistants, and other applications that involve processing and understanding user-generated text. The other options, Azure Cognitive Search (A), Translator (B), and Speech (D), are not specifically designed for intent extraction from user inputs.

    Source: Adapted from community discussion — Certification_Champs

    References

    • Microsoft Learn

    Next question

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

AI-900 practice, question 131. 236 questions available.