Deep Learning By Example

Building the model

In order to build the encoder, we need to figure out how many pixels each MNIST image will have so that we can figure out the size of the input layer of the encoder. Each image from the MNIST dataset is 28 by 28 pixels, so we will reshape this matrix to a vector of 28 x 28 = 784 pixel values. We don't have to normalize the images of MNIST because they are already normalized.

Let's start off building our three components of the model. In this implementation, we will use a very simple architecture of a single hidden layer followed by ReLU activation, as shown in the following figure:

Figure 6: Encoder-decoder architecture ...