Which Azure service can use the prebuilt receipt model in Azure AI Document Intelligence?
Answer(s): A
You can use the prebuilt receipt model in Azure AI Document Intelligence through the Azure AI Foundry portal by selecting the "Vision + Document" tile, choosing the "Receipts" prebuilt model, and then running the analysis on a sample receipt image. Azure AI Document Intelligence's prebuilt models, including the receipt model, are accessible and integrated within the Azure AI Foundry portal, allowing you to extract key information from documents like merchant name, transaction dates, and line items without custom training.
https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/model-overview
HOTSPOT (Drag and Drop is not supported)Select the answer that correctly completes the sentence.Hot Area:
Box: obtain approval based on their intended usageAs part of the Microsoft responsible AI principles, customers must _________ before they can use Azure OpenAI.Microsoft legal resources, Limited access to Azure OpenAI ServiceRegistration processAzure OpenAI requires registration and is currently only available to approved enterprise customers and partners. Customers who wish to use Azure OpenAI are required to submit a registration form.Customers must attest to any and all use cases for which they will use the service (the use cases from which customers may select will populate in the form after selection of the desired model(s) in question 22 in the initial registration form). Customers who wish to add additional use cases after initial onboarding must submit the additional use cases using this form. The use of Azure OpenAI is limited to use cases that have been selected in a registration form. Microsoft may require customers to re-verify this information. Read more about example use cases and use cases to avoid here.
https://learn.microsoft.com/en-us/legal/cognitive-services/openai/limited-access
What is an example of a Microsoft responsible AI principle?
Answer(s): C
Responsible AI principles* Fairness: AI systems should treat all people fairly. Reliability and safety: AI systems should perform reliably and safely. Privacy and security: AI systems should be secure and respect privacy. Inclusiveness: AI systems should empower everyone and engage people.* Etc.
https://learn.microsoft.com/en-us/azure/cloud-adoption-framework/strategy/responsible-ai
What should you do to reduce the number of false positives produced by a machine learning classification model?
Answer(s): D
If you have a classifier which calculates a real values score and then a threshold is applied to define what is classified as positive or negative. By changing this threshold you can decrease the number of false positives at the expense of increasing the number of false negatives.
https://www.quora.com/Why-does-my-artificial-neural-network-predict-too-many-false-positives-FP
Box: numericWhen building a K-means clustering model, all features must have a data type of______.K-means is one of the simplest and the best known unsupervised learning algorithms.Select the Normalize features option if you want to normalize features before training. If you apply normalization, before training, the data points are normalized to [0,1] by MinMaxNormalizer.
https://learn.microsoft.com/en-us/azure/machine-learning/component-reference/k-means-clustering
Post your Comments and Discuss Microsoft AI-900 exam prep with other Community members: