Summary

In this chapter, we have learned about the basic concepts of the classification problem. A classifier is a system that's able to identify the class of a new objective based on knowledge extracted from a series of samples. Different types of classification techniques have been explored—Naive Bayes, Mixture Gaussian, discriminant analysis, KNN, and SVM.

Then, we looked at Bayesian decision theory. Bayesian decision theory is an approach to statistical inference in which the probabilities are not interpreted as frequencies, proportions, or similar concepts, but rather as levels of confidence in the occurrence of a given event. 

In the second part of this chapter, we dealt with a practical case where we used the concept for heart disease classification using Keras. The basic concepts of classification methods and how to implement them in the Keras environment has been learned.

In the next chapter, we will understand the basic concepts of prediction problems, discover multilayer neural networks, and how to implement them in the Keras environment. We will also understand how to train, test, and deploy a model. We will learn how to address a prediction problem to estimate the quality of concrete. We will also learn how to evaluate the model's performance. Finally, we will learn how to tune a model to improve the model's performance.