The addition of Layer objects offers an easy mechanism for building specialized types of neural networks, including the following:

The new Sequential command allows one or more Layers to be stacked together, feeding the output from one layer into the next as input. This allows you to build sophisticated special-purpose neural networks by composing layers of different types.

Both Layer objects and the composite models created by the Sequential command are examples of Model objects. A Model can be fed new data to generate predictions and can also be saved to a file in the standard HDF5 file format.$$

In this example we build a Sequential model with DenseLayers to model the Pima diabetes dataset, generating predictions about whether individuals will be diagnosed with a diabetes based on other diagnostic measurements included in the dataset.

This dataset is originally from the United States National Institute of Diabetes and Digestive and Kidney Diseases. All patients here are females at least 21 years old of Pima Indian heritage.

Source:
Pima Indian Diabetes Database, https://www.kaggle.com/uciml/pima-indians-diabetes-database.  Data originally published in:

We first load the data into a DataFrame:

As before, we divide the dataset into training and test data.  We are attempting to predict the last column, Outcome.

We define a neural network using the Sequential command which stacks one or more neural network layers.

We can train the data easily with the Fit command:

We now have a trained model whose accuracy we can test against the test data  or against any new data. The accuracy is not especially high but nevertheless useful for predictive purposes.

To get a sense of what how this model behaves on individuals within the dataset, we can take a slice from the test data and compare the observed vs. predicted outcome.