Fundamentals of Deep Learning

Chapter 3. Implementing Neural Networks in TensorFlow

What Is TensorFlow?

Although we could spend this entire book describing deep learning models in the abstract, we hope that by the end of this text, you not only have an understanding of how deep models work, but also that you are equipped with the skill set required to build these models from scratch for your own problem spaces. Now that we have a better theoretical understanding of deep learning models, we will spend this chapter implementing some of these algorithms in software.

The primary tool that we will use throughout this text is called TensorFlow.¹ TensorFlow is an open source software library released in 2015 by Google to make it easier for developers to design, build, and train deep learning models. TensorFlow originated as an internal library that Google developers used to build models in-house, and we expect additional functionality to be added to the open source version as it is tested and vetted in the internal flavor. Although TensorFlow is only one of several options available to developers, we choose to use it here because of its thoughtful design and ease of use. We’ll briefly compare TensorFlow to alternatives in the next section.

On a high level, TensorFlow is a Python library that allows users to express arbitrary computation as a graph of data flows. Nodes in this graph represent mathematical operations, whereas edges represent data that is communicated from one node to another. Data in TensorFlow is ...