Developing Intelligent Solutions with the Microsoft AI Platform

What is Artificial Intelligence?

In this chapter you will get a short overview about what AI exactly is, and what we can do with it.

• Definitions of Artificial Intelligence
• Domains of Artificial Intelligence
• History, Current State and Future

Bots

Bots are the future! They are applications that interact naturally with users on social media, websites, Alexa, etc. But how do you create a proper bot?

• The Microsoft Bot Framework
• Debugging your bot with the bot Emulator
• Turns, Messages and Activities
• Designing a Dialog Flow
• Prompts, Waterfalls and Components
• LAB: Build a Crime Scene Investigation Bot

Machine Learning

This module presents the theoretical background in Machine Learning required for the next modules.

• Supervised vs Unsupervised
• Machine Learning Process
• Deep Learning
• Data Preparation
• Tools

Azure Cognitive Services

Your intelligent app needs to understand its environment and make decisions. For that you can use pre-trained cognitive services that detect sentiment, recognize speakers, understand pictures, etc.

• What is Cognitive services?
• Image Classification, Recognition and moderation
• Person Identification
• Speech-to-text, text-to-speech
• Speaker recognition and real-time translation
• Visual Search
• QnA
• LAB: License Plate Detection

Natural Language Processing with LUIS

Your application would be useless if they didn’t understand their users. LUIS allows us to create models to interpret what the user wants.

• The Language Understanding Intelligent Services (LUIS)
• Intents, Entities and Utterances
• Using prebuilt models
• Entity types
• Training and testing LUIS
• Calling LUIS from a bot
• Integrating LUIS with Speech
• Comparison with Watson
• LAB: Adding Natural Language Processing to the CSI Bot

Azure Machine Learning Designer

What if Cognitive Services is not enough? Time to create your own Artificial Intelligence. Azure Machine Learning allows you to “learn” from existing data, so you can make predictions for new data. In this topic we will look at the low-code option using the designer.

• Working with Datasets
• Data Preparation
• Exploring modelling techniques
• Training and evaluating models
• Automated ML
• DevOps for ML
• LAB: Predicting Crimes

ML.NET

ML.NET is all about bringing Machine Learning to your .NET application.

• Loading and Transforming Data
• Prediction and Evaluation
• Importing and Exporting Models
• Experiments
• Automated Machine Learning
• LAB: Hearth Disease Detection

Exposing your content to AI with Search

If your intelligent app needs to supply useful information to your customers, it needs to be able to access and search the information you have to offer. In this chapter you will learn how to make content searchable, and how to query your content intelligently.

• Setting up Search Indexing
• Filtering, Sorting, Facets, …
• Query Syntax
• Cognitive Search and Content Augmentation
• Consuming your Search Service
• LAB: Searching License Plates