Machine Learning
Machine Learning is an area of Artificial Intelligence research concerned with developing computational theories of learning processes and building machines that learn (Gilmore & Self 1988).
A popular definition of learning itself is a "change in a system that allows it to perform better the second time on repetition of the same task or on another task drawn from the same population" (Simon 1983).
The key element of this definition of learning is skill refinement. In living systems this skill refinement is achieved through the acquisition and application of knowledge. All intelligent organisms must be able to learn in order to adapt and at a more fundamental level survive.
Consequently the ability to learn is seen as a key indicator of intelligence and so a basic requirement of artificially intelligent systems. Given the enormity and often changing nature of the tasks that Artificial Intelligence systems need to conquer the ability to learn is seen as fundamental.
One application area where machine learning has been applied is in the development of Intelligent Tutoring Systems. This chapter reviews a number of machine learning techniques which have been used in Intelligent Tutoring Systems along with the systems that use them. The systems are categorised by the style of Machine Learning technique which are used.
Authored by Serengul Smith
E-mail to:
serengul1@mdx.ac.uk
School of Computing Science Middlesex University
Revised: September 20, 1998