TensorFlow for deep learning—implementing neural networks

What is TensorFlow?

The primary software tool that we will use throughout this lesson is called TensorFlow. 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 they are 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.

At 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 are represented as tensors, which are multidimensional arrays. Although this framework for thinking about computation is valuable in many different fields, TensorFlow is primarily used for deep learning in practice and research.

Thinking about neural networks as tensors and vice versa isn’t trivial, but it is a skill that we will develop through the course of this lesson. Representing deep neural networks in this way allows us to take advantage of the speedups afforded by modern hardware (i.e., GPU acceleration ...