HomeAbout MeBlogContact

AI-100 One Stop Guide to Prepare & Pass Azure AI Engineer Associate Certification Exam

By Naveen Bhati
Published in AI, ML & Data
April 18, 2020
13 min read

Image Source: Microsoft Training and Certifications

I just got my AI-100 Microsoft Azure AI Engineer Associate Certification. I took this exam as part of my Microsoft Cloud Solution Architect certification path and also because I am fascinated to learn and develop AI, machine learning, deep learning solution, and applications.

There are not many online courses available specifically for AI-100 exam and/or I didn’t come across if there are any hence I started documenting the research and resources and approach I used to prepare for AI-100 which lead me to pass the exam in the first attempt.

So it is now time that I share my complete preparation guide to hopefully help anyone who is currently preparing or thinking to prepare for AI-100 or for anyone who is curious bout AI on Microsoft Azure.

Here are some resources that you may find useful before actually diving into preparation -

  • Microsoft Training and Certifications Details
  • AI-100 exam information

Now that we are familiar with what the exam is about and prerequisite, let’s start understanding topic that will be covered as part of the exam

  • Analyze solution requirements (25-30%)
  • Design AI solutions (40-45%)
  • Implement and monitor AI solutions (25-30%)

Full details on each of the above topics can be found here.

Tip 1: Always do hands-on exercises to put theory into practice using Microsoft labs or on Azure Portal.

Online learning resources that I’ve used -

Tip 2: Do not solely rely on practice test(s) and go through all relevant Microsoft Documentations (I’ve provided all relevant links below in this post.)

Microsoft Documentations and blogs that I went through to prepare for AI-100

(I’d highly recommend reading every single documentation below.)

Azure Cognitive Services

  1. Computer Vision | Microsoft Azure
  2. Tutorial: REST and AI over Azure blobs - Azure Cognitive Search | Microsoft Docs
  3. Facial Recognition | Microsoft Azure
  4. Cognitive Services—APIs for AI Developers | Microsoft Azure
  5. Moderate text with custom term lists - Content Moderator - Azure Cognitive Services | Microsoft Docs
  6. Language Understanding (LUIS) | Microsoft Azure
  7. Example: Use the Large-Scale feature - Face - Azure Cognitive Services | Microsoft Docs
  8. Real time Conversation Transcription (Preview) - Speech service - Azure Cognitive Services | Microsoft Docs
  9. What is the Anomaly Detector API? - Azure Cognitive Services | Microsoft Docs
  10. Docker containers - LUIS - Azure Cognitive Services | Microsoft Docs
  11. Test your LUIS app - Azure Cognitive Services | Microsoft Docs
  12. Running Cognitive Services on Azure IoT Edge | Blog y actualizaciones de Azure | Microsoft Azure
  13. Use a Bing Web Search client library - Azure Cognitive Services | Microsoft Docs
  14. Customization - Microsoft Translator for Business
  15. Bing Statistics
  16. Real-time Twitter sentiment analysis with Azure Stream Analytics | Microsoft Docs
  17. Image classification on Azure - Azure Architecture Center | Microsoft Docs
  18. Real-time fraud detection - Azure Example Scenarios | Microsoft Docs
  19. What is Video Indexer? - Azure Media Services | Microsoft Docs
  20. Facial Recognition | Microsoft Azure
  21. Anomaly detection in Azure Stream Analytics | Microsoft Docs

Azure Bot

  1. Bot Service templates - Bot Service - Bot Service | Microsoft Docs
  2. Requirements and considerations for application-hosted media bots - Teams | Microsoft Docs
  3. Chatbot for hotel reservations - Azure Architecture Center | Microsoft Docs
  4. Pricing - Azure Bot Service | Microsoft Azure
  5. Connect a bot to the Web Chat channel - Bot Service - Bot Service | Microsoft Docs
  6. GitHub - microsoft/botframework-sdk: Bot Framework provides the most comprehensive experience for building conversation applications.
  7. Send welcome message to users - Bot Service - Bot Service | Microsoft Docs
  8. Bot Service Compliance - Bot Service - Bot Service | Microsoft Docs
  9. Deploy your bot - Bot Service - Bot Service | Microsoft Docs
  10. Bot analytics - Bot Service - Bot Service | Microsoft Docs

Azure IoT

  1. What is Azure IoT Edge | Microsoft Docs
  2. Azure Stream Analytics on IoT Edge | Microsoft Docs
  3. Compare Azure IoT Hub to Azure Event Hubs | Microsoft Docs
  4. Processing data from IoT Hub with Azure Functions - Code Samples | Microsoft Docs
  5. Understand Azure IoT Hub security | Microsoft Docs
  6. Tutorial - Stream Analytics at the edge using Azure IoT Edge | Microsoft Docs
  7. Real-time data visualization of data frm Azure IoT Hub – Power BI | Microsoft Docs
  8. Running Cognitive Services on Azure IoT Edge | Blog y actualizaciones de Azure | Microsoft Azure
  9. Store block blobs on devices - Azure IoT Edge | Microsoft Docs
  10. Detect anomalies at the edge in a solution tutorial - Azure | Microsoft Docs

Azure Machine Learning

  1. Secure web services using TLS - Azure Machine Learning | Microsoft Docs
  2. Compute context for script execution on Machine Learning Server | Microsoft Docs
  3. What are FPGA - how to deploy - Azure Machine Learning | Microsoft Docs
  4. Manage roles in your workspace - Azure Machine Learning | Microsoft Docs
  5. Control web services permissions with roles RBAC - Machine Learning Server | Microsoft Docs
  6. Export to Hive Query - ML Studio (classic) - Azure | Microsoft Docs
  7. Tutorial: Create your first ML experiment - Azure Machine Learning | Microsoft Docs
  8. Machine learning overview - Azure HDInsight | Microsoft Docs
  9. Enable logging in Azure Machine Learning | Microsoft Docs
  10. On-premises SQL Server - ML Studio (classic) - Azure | Microsoft Docs
  11. Experimentation using Azure Machine Learning | Azure Blog and Updates | Microsoft Azure
  12. Machine Learning Modules - ML Studio (classic) - Azure | Microsoft Docs
  13. Anomaly detection in Azure Stream Analytics | Microsoft Docs
  14. Collect data on your production models - Azure Machine Learning | Microsoft Docs
  15. Excel add-in for web services - ML Studio (classic) - Azure | Microsoft Docs
  16. MLOps: ML model management - Azure Machine Learning | Microsoft Docs
  17. Monitor and collect data from Machine Learning web service endpoints - Azure Machine Learning | Microsoft Docs
  18. Monitor and collect data from Machine Learning web service endpoints - Azure Machine Learning | Microsoft Docs
  19. Manage notebooks - Azure Databricks | Microsoft Docs
  20. What are ML Pipelines? - Databricks

Azure Kubernetes Service

  1. Use the cluster autoscaler in Azure Kubernetes Service (AKS) - Azure Kubernetes Service | Microsoft Docs
  2. SSH into Azure Kubernetes Service (AKS) cluster nodes - Azure Kubernetes Service | Microsoft Docs
  3. Kubernetes on Azure tutorial - Prepare an application - Azure Kubernetes Service | Microsoft Docs

Other Useful Materials

  1. Integration runtime - Azure Data Factory | Microsoft Docs

  2. Examples & common scenarios - Azure Logic Apps | Microsoft Docs

  3. Choosing a data storage technology - Azure Architecture Center | Microsoft Docs

  4. Data partitioning guidance - Best practices for cloud applications | Microsoft Docs

  5. Use the Azure portal to configure customer-managed keys - Azure Storage | Microsoft Docs

  6. How to generate and transfer HSM-protected keys for Azure Key Vault - Azure Key Vault | Microsoft Docs

  7. Ad hoc reporting queries across multiple databases - Azure SQL Database | Microsoft Docs

  8. Choose a real-time and stream processing solution on Azure | Microsoft Docs

  9. What are Apache Hadoop and MapReduce - Azure HDInsight | Microsoft Docs

  10. Audit activity reports in the Azure Active Directory portal | Microsoft Docs

  11. Batch processing - Azure Architecture Center | Microsoft Docs

  12. What is Azure Event Hubs? - a Big Data ingestion service | Microsoft Docs

  13. Create a function that integrates with Azure Logic Apps | Microsoft Docs

  14. Choosing a real-time message ingestion technology - Azure Architecture Center | Microsoft Docs

  15. Data Factory - Data Integration Service | Microsoft Azure

  16. Azure Stream Analytics on IoT Edge | Microsoft Docs

  17. What is Apache Hive and HiveQL - Azure HDInsight | Microsoft Docs

  18. Hybrid Connections (Preview) | Azure Blog and Updates | Microsoft Azure

  19. Azure Data Lake vs Azure Blob Storage in Data Warehousing

  20. Streaming at scale in Azure HDInsight | Microsoft Docs

  21. Azure VM sizes - GPU - Azure Virtual Machines | Microsoft Docs

  22. Introduction to Azure Data Factory - Azure Data Factory | Microsoft Docs

  23. Azure Stream Analytics output to Azure Cosmos DB | Microsoft Docs

  24. What is Apache Spark - Azure HDInsight | Microsoft Docs

  25. What is Interactive Query in Azure HDInsight? | Microsoft Docs

  26. Real time processing - Azure Architecture Center | Microsoft Docs

  27. Azure built-in roles for Azure RBAC | Microsoft Docs

  28. An introduction to Apache Kafka on HDInsight - Azure | Microsoft Docs

  29. What is Azure Databricks? | Microsoft Docs

  30. Virtual Machine series | Microsoft Azure

  31. Validation - SQL Server Master Data Services | Microsoft Docs

  32. Understand outputs from Azure Stream Analytics | Microsoft Docs

  33. What is the Azure Stack Development Kit (ASDK)? - Azure Stack Development Kit (ASDK) | Microsoft Docs

  34. New capabilities to enable robust GDPR compliance | Azure Blog and Updates | Microsoft Azure

  35. Cluster types in Azure HDInsight

Azure Services, Data Storages, Analytics and types of VMs that I found useful

My notes on some of the Azure Services, Data Storages, Analytics and types of VMs that I found useful. (correct at the time of writing however I’ve provided links to Microsoft Documentation for each one of the Azure services below to refer to the latest)

Azure Event Hubs is a real-time streaming platform and event ingestion service, capable of receiving and processing millions of events per second. Event Hubs can process and store events, data, or telemetry produced by distributed software and devices. Data sent to an event hub can be transformed and stored by using any real-time analytics provider or batching/storage adapters.

Event Hubs represents the “front door” for an event pipeline, often called an event ingestor in solution architectures. An event ingestor is a component or service that sits between event publishers and event consumers to decouple the production of an event stream from the consumption of those events. Event Hubs provides a unified streaming platform with time retention buffer, decoupling event producers from event consumers.

  • Key architecture components
    • Event producers
    • Consumer groups
    • Throughput units
    • Event receivers

Azure Event Grid connects data sources and event handlers. For example, use Event Grid to instantly trigger a serverless function to run image analysis each time a new photo is added to a blob storage container. Azure Event Grid Components

  • Event sources: Currently, the following Azure services support sending events toEvent Grid.
    • Azure App Configuration
    • Azure Blob Storage
    • Azure Container Registry
    • Azure Event Hubs
    • Azure IoT Hub
    • Azure Key Vault
    • Azure Machine Learning
    • Azure Maps
    • Azure Media Services
    • Azure resource groups
    • Azure Service Bus
    • Azure SignalR
    • Azure subscriptions
  • Event handlers: Currently, the following Azure services support handling eventsfrom Event Grid.
    • Azure Automation
    • Azure Functions
    • Event Hubs
    • Hybrid Connections
    • Logic Apps
    • Power Automate (Formerly known as Microsoft Flow)
    • Service Bus
    • Queue Storage
    • WebHooks

Azure Service Bus is a fully managed enterprise integration message broker. Service Bus can decouple applications and services. Service Bus offers a reliable and secure platform for asynchronous transfer of data and state. Data is transferred between different applications and services using messages. A message is in binary format and can contain JSON, XML, or just text. Some common messaging scenarios are:

  • Messaging. Transfer business data, such as sales or purchase orders, journals, or inventory movements.
  • Decouple applications. Improve reliability and scalability of applications and services. Client and service don’t have to be online at the same time.
  • Topics and subscriptions. Enable 1:n relationships between publishers and subscribers.
  • Message sessions. Implement workflows that require message ordering or message deferral.

Azure Queue Storage is a service for storing large numbers of messages. You access messages from anywhere in the world via authenticated calls using HTTP or HTTPS. A queue message can be up to 64 KB in size. A queue may contain millions of messages, up to the total capacity limit of a storage account. Queues are commonly used to create a backlog of work to process asynchronously.

Azure Notification Hubs provide an easy-to-use and scaled-out push engine that enables you to send notifications to any platform (iOS, Android, Windows, etc.) from any back-end (cloud or on-premises). Here are a few example scenarios:

  • Send breaking news notifications to millions with low latency.
  • Send location-based coupons to interested user segments.
  • Send event-related notifications to users or groups for media/sports/finance/gaming - applications.
  • Push promotional contents to applications to engage and market to customers.
  • Notify users of enterprise events such as new messages and work items.
  • Send codes for multi-factor authentication.

Azure Stream Analytics is an event-processing engine that can analyze high volumes of data streaming from devices and other data sources. It also supports extracting information from data streams to identify patterns and relationships. These patterns can trigger other downstream actions.

  • How does Stream Analytics work?
    • An Azure Stream Analytics job consists of an input, query, and an output.
    • Stream Analytics ingests data from Azure Event Hubs, Azure IoT Hub, or Azure Blob Storage.
    • The query, which is based on SQL query language, can be used to easily filter, sort, aggregate, and join streaming data over a period of time. You can also extend this SQL language with JavaScript and C# user defined functions (UDFs).
    • Option to easily adjust the event ordering options and duration of time windows when preforming aggregation operations through simple language constructs and/or configurations.

Azure Data Factory is the cloud-based ETL and data integration service that allows you to create data-driven workflows for orchestrating data movement and transforming data at scale. Using Azure Data Factory, you can create and schedule data-driven workflows (called pipelines) that can ingest data from disparate data stores. You can build complex ETL processes that transform data visually with data flows or by using compute services such as Azure HDInsight Hadoop, Azure Databricks, and Azure SQL Database.

Additionally, you can publish your transformed data to data stores such as Azure SQL Data Warehouse for business intelligence (BI) applications to consume. Ultimately, through Azure Data Factory, raw data can be organized into meaningful data stores and data lakes for better business decisions.

Big data requires service that can orchestrate and operationalize processes to refine these enormous stores of raw data into actionable business insights. Azure Data Factory is a managed cloud service that’s built for these complex hybrid extract-transform-load (ETL), extract-load-transform (ELT), and data integration projects.

Azure HDInsight is a managed, full-spectrum, open-source analytics service in the cloud for enterprises. You can use open-source frameworks such as Hadoop, Apache Spark, Apache Hive, LLAP, Apache Kafka, Apache Storm, R, and more.

  • Azure HDInsight Cluster Types.

    • Apache Hadoop - A framework that uses DHS, YARN resource management, and a simple MapReduce programming model to process and analyze batch data in parallel.The Hadoop ecosystem includes related software and utilities, including Apache Hive, Apache HBase, Spark, Kafka, and many others.**
    • Apache Spark - An open-source, parallel-processing framework that supports in-memory processing to boost the performance of big-data analysis applications.
    • Apache HBase - A NoSQL database built on Hadoop that provides random access and strong consistency for large amounts of unstructured and semi-structured data—potentially billions of rows times millions of columns.
    • ML Services - A server for hosting and managing parallel, distributed R processes. It provides data scientists, statisticians, and R programmers with on-demand access to scalable, distributed methods of analytics on HDInsight.
    • Apache Storm - A distributed, real-time computation system for processing large streams of data fast. Storm is offered as a managed cluster in HDInsight.
    • Apache Interactive Query - In-memory caching for interactive and faster Hive queries.
    • Apache Kafka - An open-source platform that’s used for building streaming data pipelines and applications. Kafka also provides message-queue functionality that allows you to publish and subscribe to data streams.

Azure Databricks is a fast, easy, and collaborative Apache Spark-based analytics service. For a big data pipeline, the data (raw or structured) is ingested into Azure through Azure Data Factory in batches, or streamed near real-time using Kafka, Event Hub, or IoT Hub. This data lands in a data lake for long term persisted storage, in Azure Blob Storage or Azure Data Lake Storage. As part of your analytics workflow, use Azure Databricks to read data from multiple data sources such as Azure Blob Storage, Azure Data Lake Storage, Azure Cosmos DB, or Azure SQL Data Warehouse and turn it into breakthrough insights using Spark.

Azure Data Lake Storage Gen2 is a set of capabilities dedicated to big data analytics, built on Azure Blob storage. Data Lake Storage Gen2 is the result of converging the capabilities of our two existing storage services, Azure Blob storage and Azure Data Lake Storage Gen1. Features from Azure Data Lake Storage Gen1, such as file system semantics, directory, and file level security and scale are combined with low-cost, tiered storage, high availability/disaster recovery capabilities from Azure Blob storage.

Azure SQL Data Warehouse or Azure Synapse Analytics is an analytics service that brings together enterprise data warehousing and Big Data analytics. It gives you the freedom to query data on your terms, using either serverless on-demand or provisioned resources—at scale. Azure Synapse brings these two worlds together with a unified experience to ingest, prepare, manage, and serve data for immediate BI and machine learning needs.

Azure IoT Edge moves cloud analytics and custom business logic to devices so that your organization can focus on business insights instead of data management. Scale out your IoT solution by packaging your business logic into standard containers, then you can deploy those containers to any of your devices and monitor it all from the cloud.

Analytics drives business value in IoT solutions, but not all analytics needs to be in the cloud. If you want to respond to emergencies as quickly as possible, you can run anomaly detection workloads at the edge. If you want to reduce bandwidth costs and avoid transferring terabytes of raw data, you can clean and aggregate the data locally then only send the insights to the cloud for analysis.

Azure IoT Edge is made up of three components:

  • IoT Edge modules are containers that run Azure services, third-party services, or your - own code. Modules are deployed to IoT Edge devices and execute locally on those devices.
  • The IoT Edge runtime runs on each IoT Edge device and manages the modules deployed to - each device.
  • A cloud-based interface enables you to remotely monitor and manage IoT Edge devices.

Azure IoT Hub is a managed service, hosted in the cloud, that acts as a central message hub for bi-directional communication between your IoT application and the devices it manages.

IoT Hub supports multiple messaging patterns such as device-to-cloud telemetry, file upload from devices, and request-reply methods to control your devices from the cloud. IoT Hub monitoring helps you maintain the health of your solution by tracking events such as device creation, device failures, and device connections.

IoT Hub’s capabilities help you build scalable, full-featured IoT solutions such as managing industrial equipment used in manufacturing, tracking valuable assets in healthcare, and monitoring office building usage.

Azure Virtual Machine Series (as of 20th April 2020)

  • A-Series - Entry-level economical VMs for dev/test

    • Example use cases include development and test servers, low traffic web servers, small to medium databases, servers for proof of concepts and code repositories.
  • Bs-Series - Economical burstable VMs

    • Example use cases include development and test servers, low-traffic web servers, small databases, micro services, servers for proof-of-concepts, build servers.
  • D-Series - General purpose compute. D-series VMs feature fast CPUs and optimal CPU-to-memory configuration, making them suitable for most production workloads.

    • Example use cases include many enterprise-grade applications, relational databases, in-memory caching and analytics. The latest generations are ideal for applications that demand faster CPUs, better local disk performance or higher memories.
  • DC-series - Protect data in use

    • Example use cases include confidential querying in databases, creation of scalable confidential consortium networks and secure multi-party machine learning algorithms. The DC-series VMs are ideal to build secure enclave-based applications to protect customers’ code and data while it’s in use.
  • E Series - Optimised for in-memory hyper-threaded applications

    • Example use cases include SAP HANA (E64s_v3 only), SAP S/4 HANA application layer, SAP NetWeaver application layer, SQL Hekaton and other large in-memory business critical workloads.
  • F-Series - Compute optimised virtual machines Example use cases include batch processing, web servers, analytics and gaming.

  • G-Series - Memory and storage optimised virtual machines

    • Example use cases include large SQL and NoSQL databases, ERP, SAP and data warehousing solutions.
  • Ls-Series - Storage optimised virtual machines

    • Example use cases include NoSQL databases such as Cassandra, MongoDB, Cloudera and Redis. Data warehousing applications and large transactional databases are great use cases as well.
  • M-Series - Memory-optimised virtual machines

    • Example use cases include SAP HANA, SAP S/4 HANA, SQL Hekaton and other large in-memory business-critical workloads requiring massive parallel compute power.
  • Mv2-Series - Largest-memory optimised virtual machines

    • Example use cases include SAP HANA, SAP S/4 HANA, SQL Hekaton and other large in-memory business-critical workloads requiring massive parallel compute power.
  • N series - The N-series is a family of Azure Virtual Machines with GPU capabilities. GPUs are ideal for compute and graphics-intensive workloads, helping customers to fuel innovation through scenarios such as high-end remote visualisation, deep learning and predictive analytics.

    • Example use cases include simulation, deep learning, graphics rendering, video editing, gaming and remote visualisation.

Last but not least, don’t forget to spend time on Microsoft Learn and Azure Documentation to find additional information to prepare your certification.

Good Luck!

Thanks for reading! 🎊 Hope you found this useful. Don’t hesitate to share, or post a comment or send me a message on LinkedIn 🙏

Please leave the comment below if you want to know more or have any question. I will be happy to help.

This article was originally published on my personal blog website.


Previous Article
Feed your Mind with Tech Events available on-demand for FREE - 2019-2020

Naveen Bhati

Engineer | QA | Cloud Architect


AI, ML & Data
All Other

Related Posts

Path to Live (PTL) - The Whats, The Whys, and The Hows
September 10, 2020
1 min
© 2021, All Rights Reserved.

Quick Links

Work with meAbout MeContactSchedule a chat

Social Media