Microsoft Certified: Azure AI Fundamentals - (AI-900) Exam Questions

Option The document is neutral is correct - The text analytics capabilities in the Language service can evaluate text and return sentiment scores and labels for each sentence. This capability is useful for detecting positive and negative sentiment in social media, customer reviews, discussion forums and more.

Using the pre-built machine learning classification model, the service evaluates the text and returns a sentiment score in the range of 0 to 1, with

• values closer to 1 being a positive sentiment.

• values closer to the middle of the range (0.5) are considered neutral or indeterminate.

• values closer to 0 are considered as negative sentiment.

Other options are not correct.

Detecting spam in emails is an example of NLP, So this scenario is not the correct use case for Conversational AI.

Natural language processing (NLP) is the area of AI that deals with creating software that understands written and spoken language.
NLP enables you to create software that can:

• Analyze and interpret text in documents, email messages, and other sources.

• Interpret spoken language and synthesize speech responses.

• Automatically translate spoken or written phrases between languages.

• Interpret commands and determine appropriate actions.

Option Adding and connecting modules on a visual canvas is correct - Azure Machine Learning designer is a drag-and-drop interface used to train and deploy models in Azure Machine Learning.

Other options are not correct.

The following options are correct:

• Implement a process of AI model validation as part of the software review process

• Establish a risk governance committee that includes members of the legal team, members of the risk management team, and a privacy officer

False. Translating speech from one language to another is not a scenario of Conversational AI. It falls under the category of Speech Recognition and Translation AI, which focuses on translating spoken language into text or another spoken language without necessarily involving a conversational interface.

Option Describe the images is correct - Computer Vision can analyze an image and generate a human-readable phrase that describes its contents. The algorithm returns several descriptions based on different visual features, and each description is given a confidence score. The final output is a list of descriptions ordered from highest to lowest confidence.

The image description feature is part of the Analyze Image API.

Other options are not correct.

Option object detection is correct - Object detection is similar to tagging, but the API returns the bounding box coordinates for each tag applied. For example, if an image contains a dog, cat and person, the Detect operation will list those objects together with their coordinates in the image.

Other options are not correct.

Option optical character recognition (OCR) is not correct - Optical character recognition (OCR) allows you to extract printed or handwritten text from images and documents.

Option scene segmentation is not correct - Scene segmentation determines when a scene changes in video based on visual cues. A scene depicts a single event and it’s composed by a series of consecutive shots, which are semantically related.

Option Load the dataset is correct - The first step in building an Azure Machine Learning classification model to identify defective products is to load the dataset. Loading the dataset is essential as it provides the data that the model will use for training and testing. Once the data is loaded, you can proceed with other steps like data preprocessing, splitting the data, and creating the classification model.

You can think of the steps to train and evaluate a classification machine learning model as:

• Prepare data: Identify the features and label them in a dataset. Pre-process, or clean and transform, the data as needed.

• Train model: Split the data into two groups, a training, and a validation set. Train a machine learning model using the training data set. Test the machine learning model for performance using the validation data set.

• Evaluate performance: Compare how close the model's predictions are to the known labels.

• Deploy: After you train a machine learning model, you need to convert the training pipeline into a real-time inference pipeline. Then you can deploy the model as an application on a server or device so that others can use it.

Other options are not correct.