Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications

Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications
Leveraging Cloud-Based Machine Learning on Azure: Real-World Applications
English | MP4 | AVC 1280×720 | AAC 48KHz 2ch | 1h 31m | 159 MB

In order to successfully incorporate AI on the popular Azure platform, you must gain a fundamental understanding of what AI is and become familiar with the local tools Azure offers. In this course, David Linthicum covers the basics of leveraging Azure for AI-based applications, including key tools and the processes for using them correctly. After going over the basics of AI processing on Azure, creating knowledge bases, and the use of AI systems in the cloud, David presents real-world use cases across a variety of industries, including healthcare, finance, law enforcement, and manufacturing. He then shows how to work with the Azure Machine Learning (AML) cloud service to build, train, and deploy machine learning models; leverage the Azure Search (AS) tool; and build an AML application.

Topics include:

  • AI processing and knowledge creation on Azure
  • The use of AI systems in cloud computing
  • The basics of the Microsoft Azure IaaS public cloud
  • AI use cases in finance, law enforcement, and education
  • Building, training, and deploying AML models
  • How Azure Search (AS) works
  • Designing your AI system
  • Training your knowledge base
  • The cost of a Microsoft AI system
  • Operating an AI system on Azure
Table of Contents

Introduction
1 Intro to AI on Azure
2 AI on Azure
3 What you should know

AI Basics
4 AI processing on Azure
5 Knowledge creation on Azure
6 AI applications on Azure
7 AI and cloud computing on Azure
8 AI and Microsoft

AI Use Cases
9 Healthcare
10 Finance
11 Law enforcement
12 Manufacturing
13 Education

Azure Machine Learning (AML)
14 AML build
15 AML train
16 AML deploy
17 AML demo

Azure Search (AS)
18 What’s different
19 Using cognitive search
20 Putting AS to good use

AML Application Walkthrough
21 Requirement
22 Design
23 Build
24 Train
25 Deployment

Other Considerations
26 Performance
27 Cost
28 Operations
29 Security
30 Governance

Conclusion
31 Resources