In Chapter 1, Getting Started with MATLAB Machine Learning, we said that machine learning is based on the concept of learning by example--knowledge gained by starting from a set of positive examples or instances of the concept to be learned, and negative examples or non-instances of the concept. In this regard, let's not forget that this concept is borrowed from the human experience, which has always been based on learning on analysis through the series of examples.

After analyzing in detail the different machine learning algorithms, it is time to put them to practice. This last chapter is meant to be a short reference, covering some of the major machine learning algorithms. In this chapter, you will just apply what has been learned. You can explore regression, classification, and clustering algorithms applied to datasets resulting from real cases. The basic concepts we have learned from the previous chapters, we will now put them into practice. If we need to reinforce these concepts, we can safely go back on our footsteps and review the topics already discussed. We will look at practical examples from raw data to extract as much knowledge as possible.

This chapter starts with solving a real-world fitting problem. Then you'll learn how to use neural networks to classify patterns. Finally, we'll perform a clustering analysis. In this way, we’ll analyze supervised and unsupervised learning algorithms.

We will cover the following topics:

• Example of fitting data
• Pattern recognition
• Clustering

At the end of the chapter, we will understand the techniques required to perform fitting analysis, pattern recognition, and clustering through a series of real cases. We will learn how to prepare data for machine learning analysis. We will also know how to perform fitting, pattern recognition, and clustering analysis in MATLAB, and how to perform preprocessing, postprocessing, and visualization to improve training efficiency and assess model performance.