Our final layer will consist of a single neuron that, using the 32 inputs from the hidden layer, will predict a single output value 
for each observation.
Putting all the layers together, our MLP network structure will look like this:
Output layer shape
Get Deep Learning Quick Reference now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
