Supervised learning §

The data is a sample of input-output patterns. A description of the data is the function that can yield the output, given the input.

What is the problem? §

The task of supervised learning is to find a deterministic function that maps any input to an output that can predict future input-output observations, minimizing the errors as much as possible.

Examples §

This problem is called supervised learning because the objects under considerations are already associated with target values, e.g., classes and real values.

Examples

1. Recognition of handwritten letters and digits
2. Prediction of stock market indexes

Types of Supervised Learning §

• Classification Learning -> the output space has no structure except whether two elements of the output are equal or not. Each element of the output space is called a class, and the algorithm that solves this problem is called classifier. The task is to assign new inputs to one of a number of discrete classes or categories. This problem characterizes most pattern recognition tasks A typical classification problem is to assign to a character bitmap the correct letter of the alphabet.
• Regression learning -> the output space is formed by the outputs representing the values of continuos variables, for instance the prediction of a stock exchange index at some future time.