Study Guide for Microsoft Azure AI-100: Designing and Implementing an Azure AI Solution

Shivam Sharma
Applied Deep Learning
5 min readMar 19, 2019
Sample AI solution on Azure

Update: 25/8/2019

  1. Bot services are a major topic now, expect many questions from it.

Microsoft has recently released a certification on artificial intelligence named AI-100: Designing and Implementing an Azure AI Solution. This certification is for engineers who have intermediate to an expert level understanding of machine learning and are responsible for deploying end-to-end AI solutions on Azure using various AI services. To understand the type of questions referer to my article here: How to prepare for Microsoft Azure certification AI-100: Designing and Implementing an Azure AI Solution?

What about the existing title of MCSA: Machine Learning?

There were two certifications leading to the title of MCSA: Machine Learning and both will retire on June 30, 2019. Two certifications were named as-

  • Exam 70–773: Analyzing Big Data with Microsoft R
  • Exam 70–774: Perform Cloud Data Science with Azure Machine Learning

Any certifications you earn prior to their retirement dates will continue to appear on your transcript in the Certification Dashboard.

Is there a transition examination available?

There is no transition examination available for professionals who already have 70-773 & 70-774 certifications. The scope of new artificial intelligence certification is far broader than the old machine learning ones.

The scope of exam 70–773: Analyzing Big Data with Microsoft R, was centered around machine learning server.

Machine learning server is a flexible enterprise platform for analyzing data at scale, building intelligent apps, and discovering valuable insights across the business with full support for Python and R. It was earlier called as Microsoft R server. Just to put things into perspective questions were mainly asked around highly-scalable, distributed set of algorithms such as RevoscaleR, revoscalepy, and microsoftML.

Similarly, the scope of exam 70–774: Perform Cloud Data Science with Azure Machine Learning was mainly centered around the Azure machine learning studio.

Microsoft Azure Machine Learning Studio is a UI based collaborative, drag-and-drop tool you can use to build, test, and deploy predictive analytics solutions on your data. Machine Learning Studio publishes models as web services that can easily be consumed by custom apps or BI tools such as Excel. It is an amazing offering. Try it out !!

Scope of AI-100

AI-100 certification is not about just Azure machine learning studio or machine learning server. It is for engineers who already have intermediate to an expert level understanding of machine learning & deep learning algorithms and now are responsible for deploying end-to-end AI solution on Azure using native as well as other supporting AI/ML services.

Certification had questions from Stream Analytics, Data Factory, Azure ML Studio, Bot Service, Event Hub, Azure IoT Hub, Azure IoT Edge, Logic App, Function, Azure ML Pipeline, Azure Notebook, Cognitive Services, Storage Account, SQL Data Warehouse. Putting things in perspective questions were framed like

  • “You are responsible for deploying CNN model …”
  • “You are deploying image processing solution…”
  • “You are deploying this… deep learning solution”

Read more about AI-100 here.

There are no labs in the certification

Study Guide:

Here is a comprehensive list of study material covering AI-100 scope & services.

Note: It is important for you to understand AI/ML/DW/Big data related architectures here https://azure.microsoft.com/en-in/solutions/architecture/ (Objective: You should be able to select the appropriate services)Links:1) Get familiar with Azure AI services 
https://azure.microsoft.com/en-in/overview/ai-platform/
2) Azure fundamentals
https://docs.microsoft.com/en-us/learn/paths/azure-fundamentals/index
3) Identify Azure storage solution to use
https://docs.microsoft.com/en-us/azure/storage/
https://www.red-gate.com/simple-talk/cloud/cloud-data/working-azure-blob-storage-service/https://azure.microsoft.com/en-in/resources/videos/build-2016-azure-data-lake-and-azure-data-warehouse-applying-modern-practices-to-your-app/4) Using Azure ML studio
https://docs.microsoft.com/en-us/learn/paths/publish-experiment-with-ml-studio/
5)Azure Data Architecture Guide
https://docs.microsoft.com/en-us/azure/architecture/data-guide/
6) Understand why and when to use these solutions (Bottom of the page)
https://azure.microsoft.com/en-in/solutions/big-data/
7) Security services and technologies available on Azure
https://docs.microsoft.com/en-us/azure/security/azure-security-services-technologies
8) Choosing a real-time message ingestion technology in Azure (Understand when & why to use them)
https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/real-time-ingestion
9) Introduction to Azure Data Science Virtual Machine for Linux and Windows
https://docs.microsoft.com/en-us/azure/machine-learning/data-science-virtual-machine/overview
10) Choosing a data pipeline orchestration technology in Azure
https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/pipeline-orchestration-data-movement
11) Azure Search
https://docs.microsoft.com/en-us/azure/search/search-lucene-query-architecture
12) Bot framework (Cover type of bot templates & when to use which)
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-design-pattern-embed-web-site?view=azure-bot-service-4.0
https://docs.microsoft.com/en-us/azure/bot-service/bot-service-overview-introduction?view=azure-bot-service-4.013) What is Language Understanding (LUIS)?
https://docs.microsoft.com/en-us/azure/cognitive-services/luis/what-is-luis
14) Azure Cognitive Services
https://docs.microsoft.com/en-in/azure/cognitive-services/
Cognitive service (Hands-on)
https://docs.microsoft.com/en-us/learn/paths/translate-speech-with-speech-services/
https://docs.microsoft.com/en-us/learn/paths/classify-images-with-vision-services/15) Azure AI solution (understand when to use what)
https://azure.microsoft.com/en-in/services/machine-learning-service/
16) Azure notebooks
https://docs.microsoft.com/en-us/azure/notebooks/
17) Stream analytics
https://docs.microsoft.com/en-in/azure/stream-analytics/stream-analytics-introduction
18) Logic App
https://docs.microsoft.com/en-in/azure/logic-apps/logic-apps-overview
19)Azure Function
https://docs.microsoft.com/en-in/azure/azure-functions/functions-overview

Do go through these pages, you will thank me later ;-)

1) Event hub features 
https://docs.microsoft.com/en-us/azure/event-hubs/event-hubs-features
2) When to use IOT hub vs Event hub in a solution
https://docs.microsoft.com/en-in/azure/iot-hub/iot-hub-compare-event-hubs
3) Store data at the edge with Azure Blob Storage on IoT Edge (preview)
https://docs.microsoft.com/en-in/azure/iot-edge/how-to-store-data-blob
4) Machine learning on Azure IoT edge (Understand Azure IoT edge concepts well)
https://docs.microsoft.com/en-in/azure/iot-edge/tutorial-deploy-machine-learning
5) Deploy function on Azure IOT edge
https://docs.microsoft.com/en-in/azure/iot-edge/tutorial-deploy-function
https://docs.microsoft.com/en-in/azure/iot-edge/tutorial-deploy-custom-visionhttps://docs.microsoft.com/en-in/azure/iot-edge/tutorial-store-data-sql-serverImage classification Solution (imp)
https://azure.microsoft.com/en-in/solutions/architecture/image-classification-with-convolutional-neural-networks/
Advance analytics on big data(imp)
https://azure.microsoft.com/en-in/solutions/architecture/advanced-analytics-on-big-data/
https://azure.microsoft.com/en-in/solutions/architecture/personalized-marketing/Bot framework
https://azure.microsoft.com/en-in/solutions/architecture/interactive-voice-response-bot/
Azure Data Factory (ADF is imp)
https://docs.microsoft.com/en-in/azure/data-factory/tutorial-hybrid-copy-data-tool
https://docs.microsoft.com/en-in/azure/data-factory/concepts-datasets-linked-serviceshttps://docs.microsoft.com/en-in/azure/data-factory/concepts-pipelines-activities

If you have a question or need further help then write in the comments below or find me on LinkedIn. Also, do let me know about any changes in questions as the examination is still in beta, so questions or pattern might change. Thanks.

If you have any comment or question, then do write them below.

To see a similar post, follow me on Medium & LinkedIn.

If you enjoyed then Clap it! Share it!!

--

--

Shivam Sharma
Applied Deep Learning

MCT | MCSE: Azure | MCSA: Machine Learning | Blockchain| R, Architect/Consultant/Trainer. I love working with cutting-edge technologies.