In this chapter, we learned how to simulate typical human brain activities through the ANN. We understood the basic concept of ANN. We saw how to build a simple neural network architecture. We explored topics such as input, hidden, and output layers; weights of connections; and the activation function.

We learned how to choose the number of hidden layers, the number of nodes within each layer, and the network training algorithm. Then, we took a tour into of the Neural Network Toolbox (which provides algorithms), pre-trained models, and apps to create, train, visualize, and simulate shallow, as well as deep, neural networks. We checked out the neural network getting started GUI, the starting point for our neural network fitting, pattern recognition, clustering, and time series analysis.

Finally, we focused on fitting data with a neural network. We saw how to use the Neural Fitting app (nftool). Then, we ran a script analysis to learn how to use neural network functions from the command line.

In the next chapter, we will learn the different types of dimensionality reduction techniques. We will understand the difference between feature selection and feature extraction. We will see how to perform the correct operation of dimensionality reduction. We'll also learn topics such as Principal Component Analysis (PCA) and factor analysis.