Supervised Learning Algorithms

Preview this chapter:

Supervised Learning Algorithms, Page 1 of 1

< Previous page | Next page > /docserver/preview/fulltext/9789815179453/chap2-1.gif

Numerous domains now employ learning algorithms. It has distinct performance metrics appropriate for them.. Based on a predetermined set of paired input-output training samples, a machine learning paradigm known as “Supervised Learning” is used to gather information about a system's input-output relationship. An input-output training sample is also known as supervised or labeled training data because the output is regarded as the input data or supervision label. Supervised learning aims to build an artificial system that can learn the mapping between input and output and predict the system's output, given new information. The learned mapping results in the classification of the input data if the output takes a limited set of discrete values representing the input's class labels. Regression of the information occurs if the output takes continuous values. The chapter details the various algorithms, technologies used and their applications.