Learn how to solve challenging machine learning problems with Tensorflow, Google’s revolutionary new system for deep learning. If you have some background with basic linear algebra and calculus, this practical book shows you how to build—and when to use—deep learning architectures. You’ll learn how to design systems capable of detecting objects in images, understanding human speech, analyzing video, and predicting the properties of potential medicines.
TensorFlow for Deep Learning teaches concepts through practical examples and builds understanding of deep learning foundations from the ground up. It’s ideal for practicing developers comfortable with designing software systems, but not necessarily with creating learning systems. This book is also useful for scientists and other professionals who are comfortable with scripting, but not necessarily with designing learning algorithms.
Table of Contents
Chapter 1. Introduction to Deep Learning
Chapter 2. Introduction to TensorFlow Primitives
Chapter 3. Linear and Logistic Regression with TensorFlow
Chapter 4. Fully Connected Deep Networks
Chapter 5. Hyperparameter Optimization
Chapter 6. Convolutional Neural Networks
Chapter 7. Recurrent Neural Networks
Chapter 8. Reinforcement Learning
Chapter 9. Training Large Deep Networks
Chapter 10. The Future of Deep Learning