Machine Learning and Microsoft Cognitive Services

Thanks to AI, modern apps are more interactive and intelligent than ever before. Microsoft's Cognitive Service APIs offer easy-to-use machine learning models that are trained on vast repositories of data to offer solutions for common use cases.
Course info
Rating
(16)
Level
Beginner
Updated
Feb 23, 2018
Duration
2h 15m
Table of contents
Description
Course info
Rating
(16)
Level
Beginner
Updated
Feb 23, 2018
Duration
2h 15m
Description

Microsoft Cognitive Services are APIs available to developers to make their applications more intelligent, engaging, and discoverable. In this course, Machine Learning and Microsoft Cognitive Services, you will learn about the APIs offered by Azure: vision, knowledge, language, speech, and search. First, you will learn the use cases of content moderation for user-generated content and customizing news feeds and searches for a target audience. Next, you will use APIs for text, image, and video moderation, including customizing the terms or images you want to block using custom lists. Finally, you will explore how the custom decision service uses reinforcement learning under the hood to personalize news feeds, and see how to integrate the service using both the pooled learning mode and the application-specific learning mode. At the end of this course, you will have hands-on experience using these pre-built machine learning models via their REST APIs.

About the author
About the author

A problem solver at heart, Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework.

More from the author
Analyzing Data with Qlik Sense
Intermediate
2h 11m
Jun 17, 2019
Using PyTorch in the Cloud: PyTorch Playbook
Intermediate
2h 21m
Apr 25, 2019
More courses by Janani Ravi
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi. My name is Janani Ravi, and welcome to this course on Machine Learning and Microsoft Cognitive Services. A little bit about myself. I have a master's degree in electrical engineering from Stanford and have worked with companies such as Microsoft, Google, and Flipkart. At Google, I was one of the first engineers working on real-time collaborative editing in Google docs, and I hold four patents for its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high- quality video content. Products developed today are personalized, interactive, and more intelligent than ever thanks to AI. Building ML models is hard, though using them is easy, and this is why Microsoft's Cognitive Service APIs are so powerful. They use models trained on vast repositories of data to offer solutions for common use cases. Content Moderation APIs allow you to track, flag, or block offensive or unwanted content on your product to help create a better experience for your users. This course shows you how you can use APIs for text, image, and video moderation. The Custom Decision Service uses reinforcement learning under the hood to personalize newsfeeds for your application. This course shows you how you can integrate this Custom Decision Service on your website using both the Pooled Learning mode, as well as the Application-specific Learning mode. Bing search offers APIs for a wide range of use cases such as autosuggest, custom search on specific sites, image and video search tailored for a specific location, and so on. With this course, you will learn how to harness the power of AI using Microsoft Cognitive Services and see real examples of integrating with these APIs.

Introduction to Cognitive Services
Hi, and welcome to this course on Microsoft Cognitive Services, which makes machine learning accessible to all. This first model is an introductory model where we look at the APIs that Cognitive Services have to offer, and we'll see how Microsoft Cognitive Services, or MCS, offers AI for everyone. It democratizes machine learning algorithms. These APIs are prebuilt machine learning models that Microsoft engineers have developed, tweaked, and run on the vast treasure trove of data that they have available to them. This allows you to tap into _____ inducing machine learning models for a number of different use cases, such content moderations, a custom decision service, APIs used by the Bing search engine for autosuggest, custom search, and video search. You have access to all of this machine learning at your fingertips without building and training any models of your own. We'll set up an Azure account to help you get up and running and then make some calls to the Computer Vision API to see what it has to offer us.

Content Moderation for Text and Images
Hi, and welcome to this module on content moderation for both and images. We'll start off by understanding why we need content moderation. Content moderation has become extremely important and a very common use case across sites and applications, especially as they accept more and more user-generated content. You want your site to be clean and inoffensive so that your customers are not irritated or angry with you when they come visit, which is why you need text and image moderation. And Azure provides an out-of-the-box way that you can get this done by simply calling a few APIs to see whether your images are inoffensive, nonracy, nonadult, and that your text is clean as well. In addition to general standards for clean content, you can also specify what is safe within your site or what is prohibited in your site by having your own custom list of text that is prohibited and images that you don't want to see within your application. This list is specifically your site and application over and about what is generally considered offensive.

Custom Decision Service for Personalizing Content
Hi and welcome to this module on the Custom Decision Service. This is artificial intelligence that you use for personalizing content to a specific user. At the time of recording this course, the Custom Decision Service helps personalize newsfeeds to individual users. All popular news sites nowadays offer feeds in terms of RSS feeds or atom feeds. These feeds are constantly updated and refreshed with the latest information from around the world on various topics. The Custom Decision Service accepts a number of these feeds as inputs and then ranks the news articles based on old user opinions. These are user opinions collected from across all users who use the Custom Decision Service. This is useful when your news app doesn't generate much traffic on its own. You can rely on other users in order to determine what the most popular articles are. If you have a high-traffic application and you want to customize news articles only based on the traffic to your specific site, that's possible as well using the Custom Decision Service.

The Bing Web Search APIs
Hi and welcome to this module where we look at the Bing web search APIs offered by Microsoft Cognitive Services. If your organization has a website or an application which is powered using Bing Search, these Cognitive Services APIs will help you customize those search results. You might want to ensure that your organization's search is safe, that it doesn't inadvertently show adult or racy content. That is also possible to configure using these search APIs. Let's say your organization has a partner site and you want to promote results from that site in your search results. That's also possible using the Bing Web Search APIs. You can block or promote content from specific sites. In this module, we'll get hands-on experience using these APIs. We'll set up a simple JavaScript application to implement these.