Subscription

Explore Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Learning Hub

Conferences

Free Learning

You're reading from Hands-On Artificial Intelligence on Amazon Web Services Decrease the time to market for AI and ML applications with the power of AWS

Product type Paperback

Published in Oct 2019

Publisher Packt

ISBN-13 9781789534146

Length 426 pages

Edition 1st Edition

Tools

AWS

Concepts

Artificial Intelligence

Authors (2):

Subhashini Tripuraneni

Charles Song

View More author details

Table of Contents (19) Chapters

Preface

1. Section 1: Introduction and Anatomy of a Modern AI Application FREE CHAPTER

2. Introduction to Artificial Intelligence on Amazon Web Services

3. Anatomy of a Modern AI Application

4. Section 2: Building Applications with AWS AI Services

5. Detecting and Translating Text with Amazon Rekognition and Translate

6. Performing Speech-to-Text and Vice Versa with Amazon Transcribe and Polly

7. Extracting Information from Text with Amazon Comprehend

8. Building a Voice Chatbot with Amazon Lex

9. Section 3: Training Machine Learning Models with Amazon SageMaker

10. Working with Amazon SageMaker

11. Creating Machine Learning Inference Pipelines

12. Discovering Topics in Text Collection

13. Classifying Images Using Amazon SageMaker

14. Sales Forecasting with Deep Learning and Auto Regression

15. Section 4: Machine Learning Model Monitoring and Governance

16. Model Accuracy Degradation and Feedback Loops

17. What Is Next?

18. Other Books You May Enjoy

Leave a review - let other readers know what you think

Technical requirements

To illustrate the concepts that we will cover in this chapter, we will use the ABC Millions Headlines dataset. This dataset contains approximately a million news headlines. In the github repository associated with this chapter, you should find the following files:

abcnews-date-text.zip: The input dataset
libraries-mleap: MLeap libraries (includes a .jar file and a Python wrapper for the .jar)

Let's begin by looking at the architecture of an inference pipeline.

The rest of the chapter is locked

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (2)

Tripuraneni

Subhashini Tripuraneni has several years of experience leading AI initiatives in financial services and convenience retail. She has automated multiple business processes and helped to create a proactive competitive advantage for businesses via AI. She is also a seasoned data scientist, with hands-on experience building machine learning and deep learning models in a public cloud. She holds an MBA from Wharton Business School, with a specialization in business analytics, marketing and operations, and entrepreneurial management. In her spare time, she enjoys going to theme parks and spending time with her children. She currently lives in Dallas, TX, with her husband and children.

See other products by Tripuraneni

Song

Charles Song is a solutions architect with a background in applied software engineering research. He is skilled in software development, architecture design, and machine learning, with a proven ability to utilize emerging technologies to devise innovative solutions. He has applied machine learning to many research and industry projects, and published peer-reviewed papers on the subject. He holds a PhD in computer science from the University of Maryland. He has taught several software engineering courses at the University of Maryland for close to a decade. In his spare time, he likes to relax in front of his planted aquariums, but also enjoys martial arts, cycling, and snowboarding. He currently resides in Bethesda, MD, with his wife.

See other products by Song