Microsoft - AI-900: Microsoft Certified: Azure AI Fundamentals

Sample Questions

Explanation:

Azure OpenAI includes a content filtering system that works alongside core models, including image generation models. This system works by running both the prompt and completion through a set of classification models designed to detect and prevent the output of harmful content. The content filtering system detects and takes action on specific categories of potentially harmful content in both input prompts and output completions. Variations in API configurations and application design might affect completions and thus filtering behavior.

Reference: Content filtering overview

Explanation:

The Azure AI Foundry provisioned throughput offering is a model deployment type that allows you to specify the amount of throughput you require in a model deployment. Azure AI Foundry then allocates the necessary model processing capacity and ensures it's ready for you. You can use the provisioned throughput you requested across a diverse portfolio of models that are sold directly by Azure. These models include Azure OpenAI models and newly introduced flagship model families like Azure DeepSeek, Azure Grok, Azure Llama, and more within Azure AI Foundry Models.

Provisioned throughput provides:

• A boarder model choice on the latest flagship models
• Flexibility to switch models and deployments with given provisioned throughput quota
• Significant discounts and the ability to boost your reservation utilization with a more flexible reservation choice
• Predictable performance, by providing stable max latency and throughput for uniform workloads.
• Allocated processing capacity: A deployment configures the amount of throughput. Once deployed, the throughput is available whether used or not.
• Cost savings: High throughput workloads might provide cost savings vs token-based consumption.

Reference: What is provisioned throughput?

Explanation:

Every prediction from an Azure Machine Learning model is associated with a confidence score, which indicates the level of confidence with which the prediction was made.

One of the easiest methods to minimize the outcomes of a certain case is simply changing the decision boundary line from the basic 0.5 to above (when reducing False Positives) or below (when reducing False Negatives). It should be noted that by doing this, the possibility of False Positives increases. In other words, by decreasing the False Negatives we are increasing the False Positives.

Reference: Evaluate automated machine learning experiment results

Explanation:

Recall measures how well the model identifies actual positive cases and precision is the ability of a model to avoid labeling negative samples as positive.

In this case the Recall metric answers the question "Of all actual oranges, how many were detected?"

In this case, the model correctly identified 70 out of 100 actual orange images. Recall is calculated by the following formula:

True Positives / (True Positives + False Negatives) ==> 70 / (70 + 30) ==> 70 / 100 = 70%

Reference: Evaluate automated machine learning experiment results

Explanation:

Automated machine learning, also referred to as automated ML or AutoML, is the process of automating the time-consuming, iterative tasks of machine learning model development. It allows data scientists, analysts, and developers to build ML models with high scale, efficiency, and productivity all while sustaining model quality. Automated ML in Azure Machine Learning is based on a breakthrough from the Microsoft Research division.

Reference: What is automated machine learning (AutoML)?