Intelligent Mobile Projects with TensorFlow: Build 10+ Artificial Intelligence apps using TensorFlow Mobile and Lite for iOS, Android, and Raspberry Pi - Softcover

Tang, Jeff

Softcover

ISBN 10: 1788834542 ISBN 13: 9781788834544

Publisher: Packt Publishing, 2018

Synopsis

Create Deep Learning and Reinforcement Learning apps for multiple platforms with TensorFlow

Key Features:

• Build TensorFlow-powered AI applications for mobile and embedded devices
• Learn modern AI topics such as computer vision, NLP, and deep reinforcement learning
• Get practical insights and exclusive working code not available in the TensorFlow documentation

Book Description:

As a developer, you always need to keep an eye out and be ready for what will be trending soon, while also focusing on what's trending currently. So, what's better than learning about the integration of the best of both worlds, the present and the future? Artificial Intelligence (AI) is widely regarded as the next big thing after mobile, and Google's TensorFlow is the leading open source machine learning framework, the hottest branch of AI. This book covers more than 10 complete iOS, Android, and Raspberry Pi apps powered by TensorFlow and built from scratch, running all kinds of cool TensorFlow models offline on-device: from computer vision, speech and language processing to generative adversarial networks and AlphaZero-like deep reinforcement learning. You'll learn how to use or retrain existing TensorFlow models, build your own models, and develop intelligent mobile apps running those TensorFlow models. You'll learn how to quickly build such apps with step-by-step tutorials and how to avoid many pitfalls in the process with lots of hard-earned troubleshooting tips.

What You Will Learn:

• Classify images with transfer learning
• Detect objects and their locations
• Transform pictures with amazing art styles
• Understand simple speech commands
• Describe images in natural language
• Recognize drawing with Convolutional Neural Network and Long Short-Term Memory
• Predict stock price with Recurrent Neural Network in TensorFlow and Keras
• Generate and enhance images with generative adversarial networks
• Build AlphaZero-like mobile game app in TensorFlow and Keras
• Use TensorFlow Lite and Core ML on mobile
• Develop TensorFlow apps on Raspberry Pi that can move, see, listen, speak, and learn

Who this book is for:

If you're an iOS/Android developer interested in building and retraining others' TensorFlow models and running them in your mobile apps, or if you're a TensorFlow developer and want to run your new and amazing TensorFlow models on mobile devices, this book is for you. You'll also benefit from this book if you're interested in TensorFlow Lite, Core ML, or TensorFlow on Raspberry Pi.

About this title

About the Author

Jeff Tang fell in love with classical AI more than two decades ago. After his MS in CS, he worked on Machine Translation for 2 years and then, to survive the long AI winter, he worked on enterprise apps, voice apps, web apps, and mobile apps at startups, AOL, Baidu, and Qualcomm. He developed a top-selling iOS app with millions of downloads and was recognized by Google as a Top Android Market Developer. He reconnected with modern AI in 2015 and knew that AI will be his passion and commitment for the next two decades. One of his favorite topics is to make AI available anytime anywhere and hence the book.

From the Inside Flap

Foreword

The past decade has seen the explosion of both machine learning and smartphones; today, these technologies are finally merging, and the result is an incredible variety of applications that you would have dismissed as far future Science Fiction just a few years ago. Think about it: you have already become accustomed to talking to your phone, asking it for directions, or telling it to schedule an appointment in your agenda. Your phone's camera tracks faces and recognizes objects. Games are becoming more interesting and challenging as the bots gets smarter and smarter. And countless apps use some form of artificial intelligence under the hood, in less obvious ways, such as recommending content that you will enjoy, anticipating your next trips to tell you when to leave, suggesting what to type next, and so on.

Until recently, all the intelligence happened on the server side, which meant that the user had to be connected to the internet, ideally with a fast and stable connection. The latency and service disruptions that this implied were show-stoppers for many applications. But today the intelligence is right there in the palm of your hand, thanks to tremendous hardware improvements and better Machine Learning libraries.

Most importantly, these technologies are now completely democratized: virtually any software engineer can learn to code an intelligent mobile application based on deep neural networks, using TensorFlow, Google's powerful and open source deep learning library. Jeff Tang's great and unique book will show you how to develop on-device TensorFlow- powered iOS, Android, and Raspberry Pi apps by guiding you through many concrete examples with step-by-step tutorials and hard-earned troubleshooting tips: from image classification, object detection, image captioning, and drawing recognition to speech recognition, forecasting time series, generative adversarial networks, reinforcement learning, and even building intelligent games using AlphaZero -- the improved technology built on top of AlphaGo that beat Lee Sedol and Ke Jie, the world champions of the game of Go.

This is going to be a super popular book. It's such an important topic, and it's hard to get good reliable information. So roll up your sleeves, you have an exciting journey ahead of you! What intelligent mobile application will you build?

Aurélien Géron

Former lead of YouTube's video classification team and author of the book Hands-On Machine Learning with Scikit-Learn and TensorFlow (O'Reilly, 2017)

Paris, May 11th, 2018

Edition details

• Publisher: Packt Publishing
• Publication date: 2018
• Language: English
• ISBN 10: 1788834542
• ISBN 13: 9781788834544
• Binding: Paperback
• Number of pages: 404