Since most of us understand the format of the function y=f(x), it is a good idea to use it to explain supervised learning. When having both y and x, we could run various regressions to identify the correct function forms. This is the spirit of supervised learning. For supervised learning, we have two datasets: the training data and test data. Usually, the training set has a set of input variables, such as x, and a related output value such as y (that is, the supervisory signal). A supervised learning algorithm analyzes the training data and produces an inferred function form. Then, we apply this inferred function to map our test dataset.
In this chapter, the following topics will be covered:
- A glance at supervised learning
- Classification
- Implementation of supervised learning via R, Python, Julia, and Octave
- Task view for machine learning in R
