TensorFlow for Deep Learning: From Linear Regression to Reinforcement Learning

TensorFlow for Deep Learning: From Linear Regression to Reinforcement Learning
Author: Bharath Ramsundar, Reza Bosagh Zadeh
Pub Date: 2017
ISBN: 978-1491980453
Pages: 300
Language: English
Format: PDF (Early Release)
Size: 10 Mb


With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as he or she writes—so you can take advantage of these technologies long before the official release of these titles. You’ll also receive updates when significant changes are made, new chapters are available, and the final ebook bundle is released.
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.

  • Gain in-depth knowledge of the TensorFlow API and primitives.
  • Understand how to train and tune machine learning systems with TensorFlow on large datasets.
  • Learn how to use TensorFlow with convolutional networks, recurrent networks, LSTMs, and reinforcement learning.