In this Keras tutorial we learn about 3 Ways to Build Machine Learning Models in Keras You Must Know.

In this article, we are going to build an artificial neural network using Tensor flow. We are going to build a deep neural network with multiple neurons and fully connected layers. The dataset we are going to work on belongs to a bank studying its customer to see if they will leave or stay and it contains around 10,000 observations. You will see that we will have to use the data preprocessing template we created in a previous article, and we will use a different set of tools as well. Here we will have an input vector containing a set of features and we will predict the outcome which will be a binary variable. As you know that ANN can be used for regression or classification and here we are going to do it for classification in this tutorial.

And just to test out the model, let's go ahead and load the CIFAR-10 dataset and run model.compile

Francois Chollet, in his book "Deep Learning with Python," outlines early on an overview for developing neural networks with Keras. Generalizing from a simple MNIST example earlier in the book, Chollet simplifies the network building process, as relates directly to Keras, to 4 main steps. This is not a machine learning workflow, nor is it a complete framework for approaching a problem to solve with deep learning. These 4 steps pertain solely to the portion of your overall neural network machine learning workflow where Keras comes into play. While Chollet then spends the rest of his book sufficiently filling in the necessary details to utilize it, let's take a preliminary look at the workflow by way of an example.