AI-900: Azure AI Fundamentals

List 5 types of AI workloads.

1. Machine learning 2. Anomaly detection 3. Computer vision 4. Natural Language Processing 5. Knowledge mining

Which type of AI workload provides the ability to generate bounding boxes that identify the locations of different types of vehicles in an image? A. Object Detection B. Image Classification C. Optical Character Recognition (OCR) D. Image Analysis

A. Object Detection

Which type of service provides a platform for conversational AI? A. Bot Services B. Translator C. Semantic Segmentation D. Form Recognizer

A. bot services

In Azure, the ________ service provides an API that developers can use to create anomaly detection solutions.

Anomaly Detector

Type of AI workload that provides the ability to automatically dtect errors or unusual activity in a system.

Anomaly detection

A feature of Azure ML that enables non-experts to quickly create an effective machine learning model from data.

Automated machine learning

Azure service that is a cloud-based platform for creating, managing, and publishing machine learning models.

Azure Machine Learning

A feature of Azure ML that provides a graphical interface enabling no-code development of machine learning solutions.

Azure Machine Learning Designer

Which AI workload scenario is an example of anomaly detection? A. Monitoring traffic to identify types of vehicles B. Monitoring the flow speed and low/high points of river water levels. C. Using a chatbot to provide an FAQ service for customer questions D. Using a search solution to search and extract information from a range of data sources.

B. Monitoring the flow speed and low/high points of river water levels.

For which scenario should you use anomaly detection? A. classifying images of plants B. detecting credit card fraud C. detecting medical issues in scanned images. D. searching for information contained in a large collection of documents.

B. detecting credit card fraud.

Which two AI workload features are part of the computer vision service? A. sentiment analysis B. entity recognition C. optical character recognition (OCR) D. Key phrase extraction E. Spatial Analysis

C. optical character recognition (OCR) E. Spatial Analysis

Which AI workload scenario is an example of NLP? A. Predicting whether customers are likely to buy a product based on previous purchases. B. Monitoring for sudden increases in quantity of failed sign-in attempts. C. Identifying objects in landscape images. D. Extracting key phrases from a business insights report.

D. Extracting key phrases from a business insights report.

Which type of AI workload provides the ability to classify individual pixels in an image depending on the object that they represent? A. Image Classification B. Image Analysis C. Object Detection D. Semantic Segmentation

D. Semantic Segmentation

A feature of Azure ML that is a cloud-based data storage and compute resources that professional data scientists can use to run data experiments code at scale.

Data and compute management

Type of computer vision that extracts information from images, including "tags" that could help catalog the image or even descriptive captions that summarize the scene shown in the image.

Image analaysis

Type of AI workload that provides the ability to extract information from large volumes of often unstructured data to create a searchable knowledge store.

Knowledge mining

(Workload) This is often the foundation for an AI system, and is the way we "teach" a computer model to make predictions and draw conclusions from data.

Machine learning

The area of AI that deals with creating software that understands written and spoken language.

NLP

Type of AI workload that provides the capability for a computer to interpret written or spoken language, and respond in kind.

Natural Language Processing

A subset of computer vision that involves training ML models to classify individual objects within an image, and identify their location with a bounding box.

Object detection

Monitoring for sudden increases in quantity of failed sign-in attempts is an _________ worklaod.

anomaly detection

Which type of AI workload would you use for a racing car telemetry system that uses sensors to proactively warn engineers about potential mechanical failures before they happen?

anomaly detection

Which type of AI workload would you use to track activity in an automated production line and identify failures?

anomaly detection

Identifying objects in landscape images is a _______ workload.

computer vision

Monitoring traffic to identify vehicle types is a type of __________ workload hat can classify images based on their contents.

computer vision

A subset of computer vision that involves training an ML model to classify images based on their contents.

image classification

Which type of computer vision would you use in a traffic monitoring solution to classify images based on the type of vehicle they contain, such as taxis, buses, cyclists, etc..

image classification

Using a search solution to extract information from a range of sources is a _______ workload.

knowledge mining

Which type of computer vision would you use for a traffic monitoring solution to identify the location of different classes of vehicle?

object detection

A subset of computer vision that involves classifying the individual pixels in an image according to the object to which they belong?

semantic segmentation

Which type of computer vision would you use for a traffic monitoring solution that overlays images with "mask" layers to highlight different vehicles using specific colors?

semantic segmentation