You would most probably remember MacGyver if you are a member of generation Y. He is famous for creating materials around him to solve unordinary solutions he faced with. Swiss army knife and duct tape would most probably be used in his practical solution. So, neural networks would be your swiss army knife in machine learning studies.
Previous experiments determine machine learning study to be handled as supervised or unsupervised.
Segmentation is a type of unsupervised learning. In this field, related group of an instance would be looked for. For example, a gym can group customers as fat and thin. However, segmentation method can be based on customer weights, body mass index or muscle and body fat ratio. In other words, there is no correct way for solution. A customer can be involved in different segments in different studies.
In contrast, labels for instances are exact in supervised learning. Suppose that you are working on dead loans. Outstanding ones of given loans are already known.
Supervised learning branches out two sub fields: classification and regression. For instance, predicting outstanding loans is a classification study. Because, instances are labeled as two classes: dead and paid ones. On the other hand, regression studies would produce continuous outputs. For example, predicting forthcoming stock price of a public firm is an example of regression.
There are different machine learning algorithms for classification and regression problems. For instance, you can build models with Support Vector Machine (SVM) for classification studies whereas use logistic regression for regression studies.
In fact, neural networks can handle both classification and regression. That’s why, I am passionately interested in this motivation.
In addition, you don’t have to do anything different in the algorithm. Feeding historical data including continuous or class labels to neural networks would handle learning. And besides, same learning algorithm would run.
So, if machine learning algorithms would be knifes then neural networks would be swiss army knife. Because, they are one of the most powerful machine learning algorithm and can be adapted into both classification and regression. Of course, the principle of right tool for the right job is still valid.