Browse Library
Sign In Start Free Trial
Close icon Search icon
Account
Browse Library Advanced Search Sign In Start Free Trial

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Learning Microsoft Cognitive Services
  • Toc
  • feedback
Learning Microsoft Cognitive Services

Learning Microsoft Cognitive Services

By : Leif Larsen Henning Larsen
close
Learning Microsoft Cognitive Services

Learning Microsoft Cognitive Services

By: Leif Larsen Henning Larsen

Overview of this book

Microsoft Cognitive Services is a set of APIs for integrating artificial intelligence in your applications to solve logical business problems. If you’re new to developing applications with AI, Learning Microsoft Cognitive Services will give you a comprehensive introduction to Microsoft’s AI stack and get you up-to-speed in no time. The book introduces you to 24 APIs, including Emotion, Language, Vision, Speech, Knowledge, and Search. Using Visual Studio, you can develop applications with enhanced capabilities for image processing, speech recognition, text processing, and much more. Moving forward, you will work with datasets that enable your applications to process various data in the form of image, video, or text. By the end of the book, you’ll be able to confidently explore Cognitive Services APIs for building intelligent applications that can be deployed for real-world business uses.
Table of Contents (14 chapters)
close
close
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
1. Getting Started with Microsoft Cognitive Services
1. Getting Started with Microsoft Cognitive Services
Cognitive Services in action for fun and life-changing purposes
Setting up the boilerplate code
Detecting faces with the Face API
An overview of different APIs
Getting feedback on detected faces
Summary
2
2. Analyzing Images to Recognize a Face
2. Analyzing Images to Recognize a Face
Analyze an image using the Computer Vision API
Diving deep into the Face API
Adding identification to our smart-house application
Knowing your mood using the Face API
Automatically moderating user content
Building your own image classifiers
Summary
3
3. Analyzing Videos
3. Analyzing Videos
Diving into Video Indexer
Unlocking video insights using Video Indexer
Summary
4
4. Letting Applications Understand Commands
chevron up
4. Letting Applications Understand Commands
Creating language-understanding models
Training a model
Summary
5
5. Speaking with Your Application
5. Speaking with Your Application
Converting text to audio and vice versa
Knowing who is speaking
Verifying a person through speech
Customizing speech recognition
Translating speech on the fly
Summary
6
6. Understanding Text
6. Understanding Text
Setting up a common core
Correcting spelling errors
Extracting information through textual analysis
Translating text on the fly
Summary
7
7. Building Recommendation Systems for Businesses
7. Building Recommendation Systems for Businesses
Providing personalized recommendations
Summary
8
8. Querying Structured Data in a Natural Way
8. Querying Structured Data in a Natural Way
Tapping into academic content using the academic API
Interpreting natural language queries
Finding academic entities in query expressions
Calculating the distribution of attributes from academic entities
Entity attributes
Creating the backend using the Knowledge Exploration Service
Defining attributes
Adding data
Building the index
Understanding natural language
Local hosting and testing
Going for scale
Answering FAQs using QnA Maker
Creating a knowledge base from frequently asked questions
Training the model
Publishing the model
Summary
9
9. Adding Specialized Searches
9. Adding Specialized Searches
Searching the web using the smart-house application
Getting the news
Searching for images and videos
Helping the user with autosuggestions
Search commonalities
Searching for visual content using Bing Visual Search
Adding a custom search
Summary
10
10. Connecting the Pieces
10. Connecting the Pieces
Completing our smart-house application
Real-life applications using Microsoft Cognitive Services
Where to go from here
Summary
11
A. LUIS Entities
A. LUIS Entities
LUIS prebuilt entities
12
B. License Information
B. License Information
Video Frame Analyzer
OpenCvSharp3
Newtonsoft.Json
NAudio
13
Index
Index

Training a model

Now that we have a working model, it is time to put it into action.

Training and publishing the model

The first step to using the model is to make sure that the model has some utterances to work with. Until now, we have added one utterance per intent. Before we deploy the application, we need more.

Think of three to four different ways to set or get the room temperature and add them, specifying the entities and intents. Also, add a couple of utterances that fall into the None intent, just for reference.

When we have added some new utterances, we need to train the model. Doing so will make LUIS develop code to recognize the relevant entities and intents in the future. This process is done periodically; however, it is wise to do it whenever you have made changes, before publication. This can be done by clicking Train in the top menu.

To test the application, you can simply enter test sentences in the Interactive Testing tab. This will show you how any given sentence is labeled...

End of Section 3
Next Section
bookmark search playlist download
font-size

Change the font size

margin-width

Change margin width

day-mode

Change background colour

Close icon Search
Country selected
Close icon Your notes and bookmarks

Delete Bookmark

Modal Close icon
Are you sure you want to delete it?
Cancel
Yes, Delete