TensorFlow for deep learning—implementing neural networks

Book description

Deep learning is a subset of machine learning, in the field of artificial intelligence. It's based on the idea that you can train a machine to learn from examples. A central method of training is through the use of neural networks.

Why is it important?

This lesson introduces you to TensorFlow, Google’s powerful open source software library for deep learning.

What you’ll learn—and how you can apply it

Learn how TensorFlow makes it easy for developers to design, build, and train deep learning models. This lesson shows you how to install TensorFlow and perform basic operations. Learn how to create and manipulate variables (taking advantage of CUDA if you have GPUs available on your computer). Compare TensorFlow with other frameworks for representing deep learning models.

This lesson is for you because…

  • You're a data scientist who is familiar with Python coding, and you need to learn how to implement neural networks using TensorFlow
  • You're a Python developer who needs to work with deep learning models in production based on TensorFlow


  • Familiarity with coding in Python
  • Some familiarity with bash command line operations
  • Basic understanding of machine learning

Materials or downloads needed in advance

  • Mac OS X or Linux computer
  • Python and PIP

Publisher resources

View/Submit Errata

Product information

  • Title: TensorFlow for deep learning—implementing neural networks
  • Author(s): Nikhil Buduma
  • Release date: August 2016
  • Publisher(s): O'Reilly Media, Inc.
  • ISBN: 9781491966198