Implementing a one-layer neural network

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.

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 that the dimensions of the data and matrix are lined up correctly.

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

How to do it...

We proceed with the recipe as follows: 

1. To create the computational graph, we'll start by loading the following necessary libraries:

   import matplotlib.pyplot as plt
   import numpy as np
   import tensorflow as tf
   from sklearn import datasets 
   

2. Now we'll load the Iris data and...