Updated Sample Questions – Microsoft Exam AI-102: Designing and Implementing a Microsoft Azure AI Solution

Artificial intelligence (AI) has been instrumental in transforming the way enterprises operate. According to reports, the global AI market is expected to reach about $60 billion by 2025. The numbers are huge, and it indicates the growing popularity of AI-driven solutions in the tech world.

If you are preparing for the Azure AI Engineer Associate exam, the following AI-102 exam dumps and answers mentioned at the end will give you a first-hand idea of the type of AI-102 exam questions that may appear in the final certification exam. You get to test your exam readiness by attending to these sample questions for Azure AI Engineer Associate (AI-102) Certification.

Questions

Q1. You have used Azure Machine Learning to train a machine learning model. How can you use the model in your application?

a. Use Azure Machine Learning to publish the model as a web service.

b. Export the model as a cognitive service.

c. You must build your application using the Azure Machine Learning designer.

Q2. How are client applications granted access to a cognitive services endpoint?

a. The application must specify a valid subscription key for the Azure resource.

b. The user must enter a username and password associated with the Azure subscription.

c. Access to cognitive services is granted to anonymous users by default.

Q3. You want to keep track of how often the subscription keys for your cognitive services resource are retrieved. How can you achieve that?

a. Regenerate the keys for your cognitive services resource.

b. Create an alert for your cognitive services resource.

c. Store the keys in Azure Key Vault.

Q4. Your organization wants to create an application that monitor the reviews on your website and notify when any negative review is posted. How can you achieve that?

a. Use the Translator service to detect profanities in comments.

b. Use the Text Analytics service to perform sentiment analysis of the comments.

c. Use the Text Analytics service to extract named entities from the comments.

Q5. Your organization uses speech synthesis and now you want to change the voice used in the service. How can you achieve that?

a. Specify a SpeechSynthesisOutputFormat enumeration in the SpeechConfig object.

b. Set the SpeechSynthesisVoiceName property of the SpeechConfig object to the desired voice name.

c. Specify a filename in the AudioConfig object.

Q6. Which object should you use to specify that the speech input to be transcribed to text is in an audio file?

a. SpeechConfig

b. AudioConfig

c. SpeechRecognizer

Q7. Your app must interpret a command to book a flight to a specified city, such as “Book a flight to Paris.” How should you model the city element of the command?

a. As an intent.

b. As an utterance.

c. As an entity

Q8. You require to add a multi-turn context for a question in an existing knowledge base. How can you achieve that?

a. Enable Active Learning for the knowledge base.

b. Add alternative phrasing to the question.

c. Add a follow-up prompt to the question.

Q9. How can you enable a conversational customer support solution through both email and web chat?

a. Create a bot for web chat. Send an automated response to email, directing users to web chat.

b. Create a bot for email, and a second bot for web chat.

c. Create a single bot and deliver it through both web chat and email channels.

Q10. With which visual feature you can generate appropriate caption for images using computer vision service?

a. Tags.

b. Description.

c. Category.

Here are the Correct Answers:

1.a

Explanation: You can use Azure Machine Learning to publish a trained model as a web service and consume it from applications through its REST interface.

2.a

Explanation: Access to a cognitive services resource is restricted through the use of subscription keys.

3. b

Explanation: You can be notified about events such as key access for your cognitive services resource by configuring an alert.

4.b

Explanation: You can use sentiment analysis to evaluate how positive or negative text is.

5.b

Explanation: To set a voice, set the SpeechSynthesisVoiceName property of the SpeechConfig to a voice name, such as “en-GB-George”.

6.b

Explanation: Use an AudioConfig to specify the input source for speech.

7.c

Explanation: The city is an entity to which the intent (booking a flight) should be applied.

8.c

Explanation: To add a multi-turn context to a question, define a follow-up prompt

9.c

Explanation: You can create a single bot and connect it to multiple channels, including web chat and email.

10.b

Explanation: To generate a caption, include the Description visual feature in your analysis.

What’s Next?

When you have tested your knowledge by answering these sample questions, I hope you have a clear stand in terms of your AI-102 exam preparation. If you feel you are lagging somewhere and you need to buckle up your preparation process, then you can enroll for CloudThat’s AI-102 certification training course to clear the final exam successfully.

CloudThat also has an exclusive Test Prep platform where learners get to practice questions to test their Azure AI-102 exam preparation. The platform offers unlimited access to Microsoft Azure AI-102 question bank, MCQs and enables you to keep track of your performance. You can go through our AI-102 exam study guide to ensure that you are on the right learning path.

So, best of luck for your exam!

Disclaimer: These questions are NOT appearing in the certification exam. I, personally or CloudThat do not have any official tie-up with Microsoft regarding the certification or the kind of questions asked in the AI-102 exam. These are my best guesses for the kind of questions to expect with AWS in general and with the examination.