Implementing different layers

It is important to know how to implement different layers. In the preceding recipe, we implemented fully connected layers. In this recipe, we will further expand our knowledge of various layers.

Getting ready

We have explored how to connect data inputs and a fully connected hidden layer, but there are more types of layers available as built-in functions inside TensorFlow. The most popular layers that are used are convolutional layers and maxpool layers. We will show you how to create and use such layers with input data and with fully connected data. First, we will look at how to use these layers on one-dimensional data, and then on two-dimensional data.

While neural networks can be layered in any fashion, one of the most common designs is to use convolutional layers and fully connected layers to first create features. If we then have too many features, it is common to use a maxpool layer.

After these layers, non-linear layers...