Rule-based machine learning

In computer science, rule-based machine learning (RBML) is a general term intended to encompass any machine learning method that identifies, learns, or evolves `rules’ to store, manipulate or apply, knowledge.  The defining characteristic of a rule-based machine learner is the identification and utilization of a set of relational rules that collectively represent the knowledge captured by the system.  This is in contrast to other machine learners that commonly identify a singular model that can be universally applied to any instance in order to make a prediction. Rule-based machine learning approaches include learning classifier systems, association rule learning, artificial immune systems, and any other method that relies on a set of rules, each covering contextual knowledge.

Rules

Rules typically take the form of an {IF:THEN} expression, (e.g.  {IF ‘condition’ THEN ‘result’}, or as a more specific example, {IF ‘red’ AND ‘octagon’ THEN ‘stop-sign’}).   An individual rule is not in itself a model, since the rule is only applicable when it’s condition is satisfied. Therefore rule-based machine learning methods typically identify a set of rules that collectively comprise the prediction model, or the knowledge base.

See also

• Learning classifier system
• Association rule learning
• Artificial immune system
• Expert system
• Decision rule
• Rule induction
• Logic programming
• Rule-based machine translation
• Genetic algorithm
• Rule-based system
• Rule-based programming
• RuleML
• Production rule system
• Business rule engine
• Business rule management system