Course Overview

In the first two days, we will focus on hands-on activities that develop proficiency in AI-oriented services such as Azure Bot Services, Azure Search, and Cognitive Services.

During days three and four, we will focus on hands-on activities that develop proficiency in AI-oriented workflows leveraging Azure Machine Learning Workbench and Services, the Team Data Science Process, Visual Studio Team Services, Azure Batch AI, and Azure Container Services.

These labs assume an introductory to intermediate knowledge of these services, and if this is not the case, then you should spend the time working through the prerequisites.

Key Learning Areas

  • Understand how to configure your apps to call Cognitive Services
  • Build an application that calls various Cognitive Services APIs (specifically Computer Vision, Face, Emotion)
  • Understand how to implement Azure Search features to provide a positive search experience inside applications
  • Configure an Azure Search service to extend your data to enable full-text, language-aware search
  • Build, train, and publish a LUIS model to help your bot communicate effectively
  • Build an intelligent bot using Microsoft Bot Framework that leverages LUIS and Azure Search
  •  Effectively log chat conversations in your bot
  • Perform rapid development/testing with Ngrok, test your bots with unit tests and direct bot communication
  • Effectively leverage the custom vision service to create image classification services that can then be leveraged by an application
  • Understand and use the Team Data Science Process (TDSP) to clearly define business goals and success criteria
  • Use a code-repository system with the Azure Machine Learning Workbench using the TDSP structure
  • Create an example environment
  • Use the TDSP and AMLS for data acquisition and understanding
  • Use the TDSP and AMLS for creating an experiment with a model and evaluation of models
  • Use the TDSP and AMLS for deployment
  • Use the TDSP and AMLS for project close-out and customer acceptance
  • Execute Data preparation workflows and train your models on remote Data Science Virtual Machines (with or without GPUs) and HDInsight Clusters running Spark
  • Manage and compare models with Azure Machine Learning
  • Explore hyper-parameters on Spark using Azure Machine Learning
  • Leverage Batch AI training for parallel training on GPUs
  • Deploy and Consume a scoring service on Azure Container Service
  • Collect and Analyze data from a scoring service in production to progress the data science lifecycle

Course Outline

Day 1
  • Introduction and Context
  • Lab 1.1: Using Portable Class Libraries to Simplify App Development with Cognitive Services
  • Whiteboard Session for Cognitive Services
  • Lab 1.2: Developing Intelligent Applications with LUIS and Azure Search
  • Summary and White-board Discussion
Day 2
  • Introduction and Context
  • Lab 2.1: Log Chat Conversations in your Bot
  • Lab 2.2: Testing your Bot
  • Summary and White-board Discussion of Azure Bot Services
  • Lab 2.3: Creating an Image Classification Application using the Custom Vision Service I
  • Lab 2.4: Creating an Image Classification Application using the Custom Vision Service II
  • Summary and White-board Discussion
Day 3
  • Introduction and Context
  • Lab 3.1: Introduction to Team Data Science Process with Azure Machine Learning
  • Lab 3.2: Comparing and Managing Models with Azure Machine Learning
  • Lab 3.3: Deploying a data engineering or model training workflow to a remote execution environment
  • Lab 3.4: Managing conda environments for Azure Machine Learning workflows
  • Summary and White-board Discussion
Day 4
  • Introduction and Context.
  • Lab 4.1: Explore hyper-parameters on Spark using Azure Machine Learning
  • Lab 4.2: Leverage Batch AI Training for parallel training on GPUs
  • Lab 4.3: Deploying a scoring service to Azure Container Service
  • Lab 4.4: Consuming the final service
  • Lab 4.5: Collect and Analyzing Data from a scoring service
  • Summary and White-board Discussion

Who Benefits

Most challenges observed by customers in these realms are in stitching multiple services together. As such, where possible, we have tried to place key concepts in the context of a broader example.

Prerequisites

  • Previous exposure to Visual Studio. We will be using it for everything we are building in the workshop, so you should be familiar with how to use it to create applications. Additionally, this is not a class where we teach you how to code or develop applications. We assume you have some familiarity with C# (intermediate level - you can learn here, but you do not know how to implement solutions with Cognitive Services.
  • Some experience developing bots with Microsoft’s Bot Framework. We won’t spend a lot of time discussing how to design them or how dialogs work. If you are not familiar with the Bot Framework, you should take this Microsoft Virtual Academy Course prior to attending the workshop.
  • Experience with the portal and be able to create resources (and spend money) on Azure. We will not be providing Azure passes for this workshop.