AI-900T00: Microsoft Azure AI Fundamentals Quiz Questions and Answers

Which of the following best describes the predictions made by a Machine Learning model?

Answer :
  • Probabilistic values based on correlations found in training data

Explanation :

Machine learning models are trained using historic data, and rely on algorithms that find statistical relationships in the data. Predictions are generally based on probability; and while models are often extremely accurate, predictions are based on a confidence score that indicates a level of probability.

You plan to use a cognitive services container in a local Docker host. Which of the following is true?

Answer :
  • The container must be able to connect to the Azure resource endpoint to send usage data for billing.

Explanation :

Client applications can access the local container directly. Data is not passed to the Azure resource, but usage data for billing is sent periodically

A data scientist has used Azure Machine Learning to train a machine learning model. How can you use the model in your application?

Answer :
  • Use Azure Machine Learning to publish the model as a web service

Explanation :

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

You plan to use the Computer Vision service to read the text in a large PDF document. Which API should you use?

Answer :
  • The Read API

Explanation :

Not only is the Read API better suited for larger images but it runs asynchronously so it will not block your application while it is running

You want to track of how often the subscription keys for your cognitive services resource are retrieved. What should you do?

Answer :
  • Create an alert for your cognitive services resource.

Explanation :

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

What is one aspect that may impair facial detection?

Answer :
  • Extreme angles

Explanation :

Best results are obtained when the faces are full-frontal or as near as possible to full-frontal