Azure AI Implementation and Monitoring
Azure Training Architect II
Artificial Intelligence, or AI, and the Machine Learning that drives it, is one of the most exciting new frontiers of technology being presented in the Cloud today. Microsoft's AI-100 is a certification path and exam that covers the Azure AI services and products available.
The Certification, as described by Microsoft:
Candidates for this exam analyze the requirements for AI solutions, recommend appropriate tools and technologies, and implements solutions that meet scalability and performance requirements.
Candidates translate the vision from solution architects and work with data scientists, data engineers, IoT specialists, and AI developers to build complete end-to-end solutions. Candidates design and implement AI apps and agents that use Microsoft Azure Cognitive Services and Azure Bot Service. Candidates can recommend solutions that use open source technologies.
Candidates understand the components that make up the Azure AI portfolio and the available data storage options.
Candidates implement AI solutions that use Cognitive Services, Azure bots, Azure Search, and data storage in Azure. Candidates understand when a custom API should be developed to meet specific requirements.
The fourth course on the AI-100 covers implementation concepts, monitoring and continuous improvement of an AI design.
This video provides an overview of the fourth course out of five covering the exam objectives for the AI-100 certification test.
About the Training Architect
Meet the Training Architect, Dan Sasse: https://www.linkedin.com/in/danielsasse/
Implement and Monitor AI Solutions (continuing)
Integrate AI Services with Solution Components
Configure Prerequisite Components and Input Datasets to Allow Consumption of Cognitive Services APIs
This long-titled study point is broken down into several different concepts in this lesson, reiterating the mechanisms needed to successfully deploy and access a Cognitive Service API. Further reading documentation: https://docs.microsoft.com/en-us/azure/storage/blobs/storage-blobs-overview https://docs.microsoft.com/en-us/azure/storage/files/storage-files-introduction https://docs.microsoft.com/en-us/azure/hdinsight/hdinsight-overview
Configure Integration with Azure Services
This lesson touches on Azure AD Security as it relates to application registration, highlighting API exposure via the AAD blade in Azure Portal. Further reading documentation: https://docs.microsoft.com/en-us/azure/active-directory/develop/active-directory-how-applications-are-added https://docs.microsoft.com/en-us/azure/active-directory/develop/quickstart-configure-app-expose-web-apis
Configure Prerequisite Components to Allow Connectivity with Bot Framework
In this lesson, we review where custom-developed bot code fits in relation to bot activities like cognitive services, support components (e.g. Azure Functions), and storage. Further reading documentation: https://docs.microsoft.com/en-us/azure/bot-service/bot-service-design-principles https://docs.microsoft.com/en-us/azure/bot-service/abs-quickstart https://docs.microsoft.com/en-us/azure/bot-service/bot-service-debug-emulator
Implement Azure Search in a Solution
In this lesson, we go over Azure Search, how it differs from Bing Search, what its components are, and where this service could work with an AI-centric design. Note from the Training Architect: This video indicates that Azure Search is not a Cognitive Service. While it may use some of the same background infrastructure, it wasn't part of the same service catalog (as opposed to the Bing Search service). However, Microsoft updated their document in November 2019, changing the name of Azure Search to Azure Cognitive Search. It looks like they're folding it into the Cognitive Services catalog after all. Further reading documentation: https://docs.microsoft.com/en-us/azure/search/search-what-is-azure-search https://docs.microsoft.com/en-us/azure/cognitive-services/bing-web-search/overview
Monitor and Evaluate the AI Environment
Identify the Differences Between KPIs, Reported Metrics, and Root Causes of the Differences
This lesson discusses some business terminology that can be expected to be used on the AI-100 Exam. We discuss the definitions of KPIs and Metrics, how they are used, and common reasons for variance between the two. Further Reading Documentation: https://docs.microsoft.com/en-us/azure/azure-monitor/learn/tutorial-app-dashboards https://docs.microsoft.com/en-us/azure/azure-monitor/platform/data-platform
Identify the Differences Between Expected and Actual Workflow Throughput
In this video, we discuss how to approach a question on the AI-100 Exam that asks about workflow throughput comparisons Further Reading Documentation: https://docs.microsoft.com/en-us/power-bi/developer/what-can-you-do https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-enable-app-insights https://docs.microsoft.com/en-us/azure/data-explorer/data-explorer-overview
Maintain the AI Solution for Continuous Improvement
This lesson defines the Developer Concept that addresses the need for Continuous Improvement; CI/CD and describes the services in Azure that are intended to assist with this. Further Reading Documentation: https://docs.microsoft.com/en-us/azure/devops/pipelines/get-started/what-is-azure-pipelines https://docs.microsoft.com/en-us/azure/machine-learning/team-data-science-process/ci-cd-flask https://docs.microsoft.com/en-us/azure/docker/
Monitor AI Components for Availability
In this lesson, we review Azure Monitor's capabilities for monitoring all the different components of what could be involved in an AI Solution design. Further Reading Documentation: https://docs.microsoft.com/en-us/azure/azure-monitor/platform/resource-logs-collect-workspace https://docs.microsoft.com/en-us/azure/azure-monitor/app/data-model https://docs.microsoft.com/en-us/azure/cognitive-services/diagnostic-logging
Recommend Changes to an AI Solution Based on Performance Data
This final lesson is going over how to recommend a change when performance metrics suggest one is needed. We discuss where design changes could be made to improve performance and touch briefly on what architecture 'scaling' is, and how to apply it. Further Reading Documentation: https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-container-support https://docs.microsoft.com/en-in/azure/aks/intro-kubernetes
Where do you go from here?
Good Work! Now: on to the last Course Segment!
Well done on completing Course Segment 4, Monitoring and Implementation, in our Certification Review of the Azure AI-100. We'd appreciate some feedback before you move on to the last Segment; Exam Preperation.
Take this course and learn a new skill today.
Transform your learning with our all access plan.Start 7-Day Free Trial