We have all of the tools needed to implement a neural network that operates on real data, so in this section we will create a neural network with one layer that operates on the `Iris` dataset.

# Implementing a one-layer neural network

# Getting ready

In this section, we will implement a neural network with one hidden layer. It will be important to understand that a fully connected neural network is based mostly on matrix multiplication. As such, it is important the dimensions of the data and matrix are lined up correctly.

Since this is a regression problem, we will use mean squared error as the loss function.