AI & ML Academy - Applied AI
Welcome to the AI & ML Academy (AIA) - Applied AI!
In this module, we’ll look at Applied AI services, including Form Recognizer, Metrics Advisor, Cognitive Search, Video Indexer, Personalizer, Anomaly Detector, and Power Virtual Agents.
Applied AI
Form Recognizer
Form Recognizer is an AI service that applies advanced machine learning to extract text, key-value pairs, tables, and structures from documents automatically and accurately. Turn documents into usable data and shift your focus to acting on information rather than compiling it.
Conceptual
- The AI Show - Ep 52: Analyze unstructured docs and more with Azure Form Recognizer - This is a great resource to understand Form Recognizer capabilites and updates.
- Applied AI Blog - A place to ask any questions you have about Form Recognizer as you work on your solutions.
Updates
- Build Recap: The Newest Features from Azure Form Recognizer - A great place to see the new features for Azure Form Recognizer
Cognitive Search
Azure Cognitive Search is a cloud search service with built-in AI capabilities that enrich all types of information to help you identify and explore relevant content at scale. Use cognitive skills for vision, language, and speech, or use custom machine learning models to uncover insights from all types of content.
Conceptual
- Knowledge Mining Solution Accelerator - A tool to get hands-on and build a knowledge mining prototype with azure cognitive search.
- Implement knowledge mining with Azure Cognitive Search - This is a good learning path to understand knowledge mining with azure cognitive search
- Indexing multiple Azure Blob Storage containers in Azure Cognitive Search - This is a good hands-on lab to understand how to index multiple blob storage containers in Azure Cog Search.
- Search over multiple search services - This shows how to combine Search Results and Relevance Scores from different indexes
- ServerlessIndexer - Another great hands on tool for a trigger indexer with Push API solution
- Azure Cognitive Search UI - Hands-On React template for Azure Cognitive Search
- Business Process Accelerator - No code solution for creating a multi-stage AI pipeline
Metrics Advisor
Metrics Advisor is a part of Azure Applied AI Services that uses AI to perform data monitoring and anomaly detection in time series data. The service automates the process of applying models to your data, and provides a set of APIs and a web-based workspace for data ingestion, anomaly detection, and diagnostics - without needing to know machine learning.
Conceptual
- MetricsAdvisorSample - This is a great hands-on lab to understand the capabilities of Azure Metrics Advisor.
- Introducing Metrics Advisor - A new Cognitive Service - An overview of metrics advisor and what is possible.
- Introducing Metrics Advisor - A new Cognitive Service - Great page for user stories.
- Detecting Methane Leaks using Azure Metrics Advisor - Blog post for use case with detecting methane leaks
- Introducing Metrics Advisor - Great video with an overview on metrics advisor
- Azure Metrics Advisor Documentation - Documentation page with quickstarts and tutorials
- Supply Chain Anomaly Detection and Root Cause Analysis with Azure Metric Advisor - Blog post with use case supply chain anomaly detection
Updates
- Protect your organization’s growth by using Azure Metrics Advisor - Blog post for new updates with metrics advisor
Personalizer
Create optimized user experiences, boost conversion and engagement, and add real-time relevance to product recommendations, with reinforcement learning–based capabilities. Personalizer can suggest general and individual layouts for users, using API calls.
Conceptual
- With reinforcement learning, Microsoft brings a new class of AI solutions to customers - Great blog post for reinforcement learning use cases
- Azure Cognitive Services - Personalizer Samples - This is a hands-on link with tutorials and resources for Personalizer
- Personalizer documentation - This link includes a lot of conceptual documentation and helpful quickstarts.
- Personalizer API Reference - API reference guide
Video Indexer
Azure Video Indexer is a cloud application built on Azure Media Services and Azure Cognitive Services. It enables you to extract the insights from your videos using Azure Video Indexer video and audio models.
Conceptual
- Video Indexer 101 Overview - This is a helpful deck with a good overview of video indexer and its features.
-
[Official Azure Media Services Video Indexer Samples](https://github.com/Azure-Samples/media-services-video-indexer) - Hands-on lab with many examples of video indexer in action
Anomaly Detector
Anomaly Detector ingests time-series data of all types and selects the best anomaly detection algorithm for your data to ensure high accuracy. Detect spikes, dips, deviations from cyclic patterns, and trend changes through both univariate and multivariate APIs.
Conceptual
- 4 sets of best practices to use Multivariate Anomaly Detector when monitoring your equipment - This is a helpful blog post with best practices.
- Time-Series Anomaly Detection Service at Microsoft - All about Univariate Anomaly Detection.
- AI Show Live-Episode 11-New to Anomaly Detector: Multivariate Capabilities - All about Multivariate Anomaly Detection
- Anomaly Detector API Samples - Hands on lab with many samples for anomaly detection
Power Virtual Agents
Power Virtual Agents lets you create powerful AI-powered chatbots for a range of requests—from providing simple answers to common questions to resolving issues requiring complex conversations. Engage with customers and employees in multiple languages across websites, mobile apps, Facebook, Microsoft Teams, or any channel supported by the Azure Bot Framework.
Conceptual
- Power Virtual Agents Blog - Blog post that describes the latest and greatest updates!
- Power Virtual Agents Demo - Helpful demo to showcase PVA capabilities.
- Power Virtual Agents Overview - This is a documentation page with a good overview on PVA along with tutorials.
Hands-on Content
Each module contains several options for hands-on learning. In most cases, there are multiple options available designed to meet your specific skilling needs, from simple tutorial/demo content to more advanced workshops. We understand that some people may just want to see demos while others want to dive deep; most are somewhere in between. Use the content that best suits you!
Suggested Hands-on Labs (HOL) / Workshops
Coming soon