Practical AI on the Google Cloud Platform

Working with AI is complicated and expensive for many developers. That’s why cloud providers have stepped in to make it easier, offering free (or affordable) state-of-the-art models and training tools to get you started. With this book, you’ll learn how to use Google’s AI-powered cloud services to do everything from creating a chatbot to analyzing text, images, and video.

Author Micheal Lanham demonstrates methods for building and training models step-by-step and shows you how to expand your models to accomplish increasingly complex tasks. If you have a good grasp of math and the Python language, you’ll quickly get up to speed with Google Cloud Platform, whether you want to build an AI assistant or a simple business AI application.

• Learn key concepts for data science, machine learning, and deep learning
• Explore tools like Video AI and AutoML Tables
• Build a simple language processor using deep learning systems
• Perform image recognition using CNNs, transfer learning, and GANs
• Use Google’s Dialogflow to create chatbots and conversational AI
• Analyze video with automatic video indexing, face detection, and TensorFlow Hub
• Build a complete working AI agent application

Table of Contents

Chapter 1. Data Science and Deep Learning

Chapter 2. Al on the Google Cloud Platform

Chapter 3. Image Analysis and Recognition on the Cloud

Chapter 4. Understanding Language on the Cloud

Chapter 5. Chatbots and Conversational Al

Chapter 6. Video Analysis on the Cloud

Chapter 7. Generators in the Cloud

Chapter 8. Building Al Assistants in the Cloud

Chapter 9. Putting Al Assistants to Work

Chapter 10. Commercializing Al

Who Should Read This Book

You will enjoy this book if you’re eager to learn and enjoy working with or seeing plenty of coding examples. I have tried to make this book accessible by minimizing the discussion of mathematics. However, you may find yourself needing some math refreshers or tutorials to grasp certain core concepts. Training models can and will take time, so patience is a must. As well, you need to understand that you will most certainly fail at what seem to be the most rudimentary of tasks. The important thing to remember is that AI is just hard; it takes dedication and commitment to understand it.

A Note on the Google AI Platform

AI is currently progressing at a ferocious rate, and many aspects of AI are breaking and/or quickly becoming dated. It is quite likely that parts of this book could become outversioned, but not to fear. Many of the examples in this book are based on very common tasks, and in many cases Google may have similar and more up-to-date examples.

Therefore, if at any time throughout this book you encounter an issue, do a quick Google search and you may see the answer to your problem in a number of places.

You will likely find that many of the code examples early on this book use very common blocks of code, and this is very much intentional. However, make sure you understand all the details of that code, including any minor changes.

Many times what appears to be just a minor difference turns out to be the reason the code was failing. Be sure you pay attention to details and understand how the code works, including the inputs and outputs.

Things You Need for This Book

Working through the examples in the book will require you to have the following knowledge or resources:

Python — You should have a good grasp of the Python language, and know how to run scripts on your own.

Desktop computer — All of the examples are provided online and in cloud services, but it is still recommended you do this on a wider-screen desktop computer for better results. Of course, for those diehards out there, using a phone will always be an option.

Mathematics — For best results, you want to have an interest in math. You don’t have to be a genius in mathematics, but an understanding at the high school or postsecondary level is recommended.

Fortitude — You need the ability to persevere through extremes, and developing AI will certainly challenge that. You will have many ups and downs learning and doing AI. Be prepared to be humble and get tough—you will need it.

Google — Googling is a skill that apparently not all people have. Make sure to keep yours current, and use Google to enhance your knowledge.

About the Author

Micheal Lanham is a proven software and tech innovator with 20 years of experience. During that time, he has developed a broad range of software applications. Including games, graphic, web, desktop, engineering, artificial intelligence, GIS and machine learning applications for a variety of industries as an R&D developer. He currently resides in Calgary, Alberta, Canada with his family.

At the turn of the millennium Micheal began working with neural networks and evolutionary algorithms in game development. He was later introduced to Unity and has been an avid developer, consultant, manager and author of multiple Unity games, graphic projects and books since.

Micheal has previously written Augmented Reality Game Development, Game Audio Development with Unity 5.x and Learn ARCore: Fundamentals of Google ARCore, Unity ML-Agents – Fundamentals of Unity Machine Learning and Hands-on Deep Learning for Games all published by Packt Publishing.