Practical Deep Learning for Cloud Mobile and Edge - TensorFlow, Keras, Python Book Video

After 2 years and multiple rewrites of 600 pages, we are visibly excited to announce our OReilly AI book titled 'Practical Deep Learning for Cloud Mobile and Edge' - 'Real-World AI & Computer Vision Projects Using Python, Keras & TensorFlow'. We walk through creating scalable, production-quality AI projects, beyond the typical MNIST examples, spanning from topics such as reverse image search engines, scaling on the cloud, deploying models to mobile and robots, to autonomous driving and reinforcement learning. We attempt to use humor, plenty of experimentation, and real-world case studies to make these concepts approachable. Our hope is that you find this book enjoyable and useful.

Chapter List:
1. Exploring the Landscape of Artificial Intelligence
2. What's in the Picture: Image Classification with Keras
3. Cats Versus Dogs: Transfer Learning in 30 Lines with Keras
4. Building a Reverse Image Search Engine: Understanding Embeddings
5. From Novice to Master Predictor: Maximizing Convolutional Neural Network Accuracy
6. Maximizing Speed and Performance of TensorFlow: A Handy Checklist
7. Practical Tools, Tips, and Tricks
8. Cloud APIs for Computer Vision: Up and Running in 15 Minutes
9. Scalable Inference Serving on Cloud with TensorFlow Serving and KubeFlow
11. Real-Time Object Classification on iOS with Core ML
12. Not Hotdog on iOS with Core ML and Create ML
13. Shazam for Food: Developing Android Apps with TensorFlow Lite and ML Kit
14. Building the Purrfect Cat Locator App with TensorFlow Object Detection API
15. Becoming a Maker: Exploring Embedded AI at the Edge
16. Simulating a Self-Driving Car Using End-to-End Deep Learning with Keras
17. Building an Autonomous Car in Under an Hour: Reinforcement Learning with AWS DeepRacer

Connect with the authors:

** Who are we? **
Between us, we have nearly 25 years of industry experience at Microsoft Research, Nvidia (self-driving team), NASA FDL, Amazon, Square, and Yahoo. During this time, we’ve taken AI research projects to production and shipped them to a billion devices (we genuinely don’t mean to sound braggy here).

** Why this book? What is unique about it? **
We provide complete examples for many of the real-life projects in the book. We discuss in-depth engineering concerns such as data collection, bias in data, model debugging, resource efficiency (CPU, memory, power), accuracy, A/B testing, monitoring, versioning, maintenance, updates, etc. The examples on our GitHub repo are readily runnable on Google Colab, or Xcode/Android Studio.

** Who is the audience for this book? **
- Students who aspire to develop a career in AI by building a portfolio of interesting projects, and prepare for internship/job opportunities/graduate studies.
- Professionals who intend to take nascent research and productionize it for millions of users.
- Those who generally seek to expand their breadth of knowledge in the field of deep learning.

** What technologies do we touch upon? **
- TensorFlow 2.x and Keras are the most prevalent ones throughout the book.
- For mobile - Swift, Core ML for iOS. Kotlin, TensorFlow Lite for Android. Fritz Labs and ML Kit.
- For hardware - AWS Deep Racer, Raspberry Pi, NVIDIA Jetson Nano, Google Coral, Intel Movidius, PYNQ-Z2, etc.

** Who is currently reading it? **
So far we are aware of engineers and researchers at organizations such as Microsoft, Apple, Google, NASA, MIT, Facebook, Amazon, Nvidia, Uber, IBM, Twitter, Lyft, Oracle, Intel, etc. who are reading the book.

If you’ve reached this far, we admire your persistence!