AI-900: Azure AI Fundamentals: Anomaly Detection

AI-900: Azure AI Fundamentals: Anomaly Detection

• discover the key concepts covered in this course
• describe the purpose and uses for anomaly detection and how AI anomaly detection can be used to identify unusual patterns, failures, and fraud
• identify the challenges of detecting anomalies in real world situations and how AI-based anomaly detection can be used to mitigate those challenges
• describe how the Azure Anomaly Detector Cognitive Service provides the tools and customization for adding anomaly detection to your apps and services
• navigate the Azure Anomaly Detector service web site and interfaces used to start an anomaly detection service you can use in the real world
• create an Azure Anomaly Detection service project and view some of the configuration options
• integrate a time series based dataset into an Azure Anomaly Detection service project
• train a best-fitting detection model on the time series data to get the best anomaly detection reporting
• deploy the Azure Anomaly Detector service using an API key for external apps to collect anomaly reports
• test and evaluate the Azure Anomaly Detector service using external data to simulate anomalies
• customize the Azure Anomaly Detection service for sensitivity, detection, and other parameters
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: : Artificial Intelligence & Machine Learning

AI-900: Azure AI Fundamentals: : Artificial Intelligence & Machine Learning

• discover the key concepts covered in this course
• describe Artificial Intelligence and how it can be used to solve business problems
• describe machine learning and how it can be used for anomaly detection, computer vision, and natural language processing
• describe datasets and how to manipulate data for those datasets
• differentiate between labeled and unlabeled data and describe why some AI models require labeled data
• describe how features are selected and used from datasets in AI algorithms
• describe regression algorithms and how they are used to make predictions
• describe classification algorithms and how they are used to classify objects or relations
• describe clustering algorithms and how they can be used to determine groupings in data
• describe how supervised machine learning models use labeled data, are simpler to build, and have more accurate results
• describe how unsupervised machine learning models use unlabeled data, which makes them more complex but more flexible than supervised machine learning
• describe how to responsibly use AI by making sure it is reliable and safe
• describe how transparency should be used with AI algorithms in a responsible way
• describe how privacy and security must be factored into responsibly creating and using AI solutions
• describe how the use of inclusiveness in AI algorithms can benefit everyone
• describe how fairness in AI algorithms results in responsible AI
• describe how governance and organizational policies provide accountability for AI responsibility
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: Authoring with the Azure ML Studio Designer

AI-900: Azure AI Fundamentals: Authoring with the Azure ML Studio Designer

• discover the key concepts covered in this course
• create and use a dataset component in Azure ML Designer
• select features from a dataset in ML Designer
• add data transformations to prepare data in ML Designer
• add normalizing and cleaning components for data in ML Designer
• view the output from different normalized and transformed datasets in Azure ML Designer
• split a dataset into a testing and evaluation set for model training and evaluation using Azure ML Designer
• add and use a regression training model in ML Designer
• configure and use a classification model in ML Designer
• use a clustering model in ML Designer
• summarize the key concepts covered in this course

The Azure Machine Learning Studio provides a proficient designer that can be used to build machine learning pipelines. In this course, you'll explore Azure ML Studio Designer and practice using its features for managing, normalizing, and transforming data for use in regression, classification, and clustering models.

You'll also learn how to select features from a dataset and create datasets for training and validating models within Studio Designer.

By the end of the course, you'll be able to use datasets, add transformations, normalize and clean data, split datasets, and configure and use a number of models, all within Azure ML Studio Designer.

This course is one of a collection that prepares learners for the Microsoft Azure AI Fundamentals (AI-900) exam.

AI-900: Azure AI Fundamentals: Computer Vision

AI-900: Azure AI Fundamentals: Computer Vision

• discover the key concepts covered in this course
• describe how computer vision works and how it can be used to solve real world problems
• recognize the features and capabilities of the Azure Computer Vision services
• identify the different Computer Vision models available for doing image classification, object detection, and image analysis
• describe how Computer Vision identifies real world items and objects
• use the Computer Vision service to analyze images
• use studio to describe and tag images used for training a classification model
• training a classifier to classify items in an image
• evaluate the results of the classifier model
• deploy and test the prediction capabilities of the Model
• train a model to detect objects in an image
• evaluate the results of an object detection model
• deploy and test the model as a service
• describe the purpose and uses of semantic segmentation
• summarize the key concepts covered in this course

Computer vision is the machine learning capability to allow computers to "see" similar to how a person can see, and be able to identify, distinguish, and interpret objects, people, and even text from images or video. In this course you will learn about the Azure ML Computer Vision service, Computer Vision Models, and how it can be trained and used to detect and classify objects in images and videos using a Classifier model and semantic segmentation. You’ll also learn how to evaluate the results of an object detection model. This course is one of a collection that prepares learners for the Microsoft Azure AI Fundamentals (AI-900) exam.

AI-900: Azure AI Fundamentals: Creating a Conversational AI Bot

AI-900: Azure AI Fundamentals: Creating a Conversational AI Bot

• discover the key concepts covered in this course
• describe the features and capabilities of a conversational AI bot
• identify business and personal uses for a conversational bot
• create a knowledgebase for a bot using QnA Maker
• populate and train a knowledgebase from sources of knowledge
• publish and test a knowledgebase
• create a Bot that uses a knowledgebase
• extend the bot framework to enhance the conversational bot
• test the bot and its use of the knowledgebase
• configure and use logging and analytics with Application Insights to analyze a bot
• publish a bot that can be used by external and channel sources
• connect the bot to standard channels to give third parties access to the conversational bot
• directly connect the bot to give conversational capabilities to a private project
• describe the purpose and uses of digital or virtual assistants
• create a simple virtual assistant leveraging Azure's bot service and Bot Builder SDK v4
• deploy a virtual assistant to Azure and test its functionality using the Bot Framework Emulator
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: Evaluating Models with the ML Designer

AI-900: Azure AI Fundamentals: Evaluating Models with the ML Designer

• discover the key concepts covered in this course
• add a Scoring model component in the ML Designer
• describe model evaluation types like MAE and R2
• use an evaluator on a model and interpret the metrics
• run and monitor a complete pipeline
• analyze the evaluation results in the output and logs section in the ML Designer
• identify and investigate the details of the evaluation results
• visualize the scoring data from the Scoring model
• investigate the logs and results that are significant when running a Regression model
• interpret the results from running a Classification model
• interpret the results and logs form running a Clustering model
• create an inference pipeline using a Python script
• add a web service output to provide external access to the model
• deploy the model as a predictive service
• test the predictive service from an external app
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: Face & Optical Character Recognition

AI-900: Azure AI Fundamentals: Face & Optical Character Recognition

• discover the key concepts covered in this course
• describe the Azure Face Detection service and how it can be used to analyze faces
• use the Computer Vision service to analyze a face to determine age
• use the video indexer to identify faces in videos
• use the Face Service to detect, recognize, and analyze faces for sentiment
• describe the Optical Character Recognition (OCR) API provided by Azure
• use the Computer Vision service to read text
• use the Computer Vision service to read text from real-life photographs
• use the Computer Vision service to read text from digitized documents
• identify the features and capabilities of the Form Recognizer service
• describe the Read API that is provided by the Form Recognizer service
• use the pre-built receipt model to get details from receipts
• use the Custom Form Recognizer model to get details from receipts and forms
• use the Form Recognizer model to identify specific fields and datatypes on a receipt
• process tabular data from a receipt or form using the Form Recognizer
• summarize the key concepts covered in this course

An advanced and powerful feature of computer vision is the ability to detect, identify, and even analyze faces and forms in images and videos. In this course, you'll learn how to use the Azure Face Detection service and Computer Vision service to determine a person's age from an image and to determine their sentiment. You'll also explore how to use the Form Recognizer service to read and process forms using Optical Character Recognition. Finally, you'll learn how to use the Receipt and Custom Form Recognizer to process fields from receipts. This course is one of a collection that prepares learners for the Microsoft Azure AI Fundamentals (AI-900) exam.

AI-900: Azure AI Fundamentals: Machine Learning with Azure Services

AI-900: Azure AI Fundamentals: Machine Learning with Azure Services

• discover the key concepts covered in this course
• describe the machine learning services provided by Azure
• describe the Azure Machine Learning Studio
• register and signup for an Azure Machine Learning Studio account and access the studio dashboard
• inspect the Azure ML Studio sidebar components used for creating machine learning workflows
• describe the features and services provided by the Azure Computer Vision Service
• describe the uses of the Custom Vision Service
• describe the features and services provided by the Azure Face service
• describe the features and capabilities of the Form Recognizer service
• identify the process and functions of Azure ML Studio for creating, running, and maintaining AI workloads
• identify and describe the features of a compute target
• describe a dataset and how they are created and managed
• manage pipelines in the Azure ML Studio interface
• describe the limitations and features of automated ML model training
• describe an experiment and how to run it in Azure ML studio
• identify and interpret the evaluation metrics for a run of a Classification model
• identify and interpret the evaluation metrics for a run of a Regression model
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: Natural Language Processing

AI-900: Azure AI Fundamentals: Natural Language Processing

• discover the key concepts covered in this course
• describe the features of Natural Language Processing (NLP)
• identify the uses and challenges of NLP
• describe the features of the NLP services provided by Azure
• identify NLP features used for handling phase extraction, entity recognition, and intents
• configure and train a language model
• use the Text Analytics service to extract key phrases
• describe the features and uses of the Azure Translator Service for translating text
• use the Translator Service to translate text
• use the Translator Service to translate speech
• summarize the key concepts covered in this course

AI-900: Azure AI Fundamentals: Using Azure Machine Learning Studio

AI-900: Azure AI Fundamentals: Using Azure Machine Learning Studio

• discover the key concepts covered in this course
• create and configure an Azure Machine Learning workspace
• create and use a compute resource using Azure ML Studio
• create and use a dataset in Azure ML Studio
• ingest data from an Azure Storage source
• ingest data from an Azure Blob storage resource
• label data within a dataset in the Azure ML Studio interface
• identify how to run test scripts manually using Notebook
• use the automated ML model to create an experiment that will automatically find the best-fit model
• run an automated ML model experiment to find the best-fit model
• evaluate the results of an automated ML model experiment to investigate the best model results
• deploy an automated ML model as a predictive service
• test an automated ML predictive service by using it to get predictions based on test data
• manage and manipulate compute resources and datastores from the Azure ML Studio
• manipulate and configure datasets and experiments, including for other team members, in Azure ML Studio
• manage stored pipelines and models in Azure ML Studio
• manage and configure endpoints in Azure ML Studio
• summarize the key concepts covered in this course

The Azure Machine Learning Studio is a complete web tool and graphical user interface for building, managing, deploying, evaluating, and testing machine learning algorithms and workloads from initial design to final deployment.

In this course, you'll investigate the different features of the Azure ML Studio interface and use it to create datasets, ingest data, create models automatically, build prediction services, and finally, manage endpoints for a machine learning model.

Furthermore, you'll explore the datastores, compute resources, experiments, pipelines, and model management interfaces that are utilized when working with Azure ML Studio.

This course is one of a collection that prepares learners for the Microsoft Azure AI Fundamentals (AI-900) exam.