Rule Induction Task
A Rule Induction Task is a inductive reasoning task that requires the creation of a rule set (from observations).
- AKA: Rule Learning Task, Rule Extraction Task.
- Context:
- Task Input: an Observed Dataset.
- Task Output: Rule Set .
- It can be solved by a Rule Induction System that implements a Rule Induction Algorithm.
- It can range from being a Supervised Rule Induction Task to being an Unsupervised Rule Induction Task.
- It can range from being a Descriptive Rule Induction Task to being a Predictive Rule Induction Task.
- Example(s):
- Counter-Example(s):
- See: Hypothesis Testing Task, Decisition Rule, Horn Clause Induction, Inductive Logic Programming, Boolean Decomposition, Patterns, Machine Learning, Scientific Model.
References
2019
- (Wikipedia, 2019) ⇒ https://en.wikipedia.org/wiki/Rule_induction Retrieved:2019-11-2.
- Rule induction is an area of machine learning in which formal rules are extracted from a set of observations. The rules extracted may represent a full scientific model of the data, or merely represent local patterns in the data.
2017a
- (Cussens, 2017) ⇒ James Cussens (2017). "Induction". In: Sammut & Webb (2017). DOI:10.1007/978-1-4899-7687-1_388
- QUOTE: Induction is the process of inferring a general rule from a collection of observed instances. Sometimes it is used more generally to refer to any inference from premises to conclusion where the truth of the conclusion does not follow deductively from the premises, but where the premises provide evidence for the conclusion. In this more general sense, induction includes abduction where facts rather than rules are inferred. (The word “induction” also denotes a different, entirely deductive form of argument used in mathematics.)
2017b
- (Furnkranz, 2017) ⇒ Johannes Furnkranz (2017). "Rule Learning". In: Sammut & Webb (2017). DOI:10.1007/978-1-4899-7687-1_744
- QUOTE: Informally, rule learning denotes all algorithms that learn or discover patterns in data, which are formulated in the form of a rule. These can be predictive (e.g., classification rules) or descriptive rules (e.g., association rules or supervised descriptive rule induction). Consequently, the learning algorithms typically differ in the type of search they use for finding these rules in the search space. Exhaustive search is more common in descriptive rule mining, whereas heuristic search using a variety of quality criteria is more commonly used in predictive rule learning. An overview of the field can be found in Fürnkranz et al. (2012).
2009
- (Grzymala-Busse, 2009) ⇒ Jerzy W. Grzymala-Busse (2009) "Rule Induction". In: Maimon O., Rokach L. (eds) "Data Mining and Knowledge Discovery Handbook". DOI:10.1007/978-0-387-09823-4_13
- QUOTE: Rule induction is one of the most important techniques of machine learning. Since regularities hidden in data are frequently expressed in terms of rules, rule induction is one of the fundamental tools of Data Mining at the same time. Usually rules are expressions of the form i f (attribute−1, value−1) and (attribute−2, value−2) and ··· and (attribute−n, value−n) then (decision, value).
Some rule induction systems induce more complex rules, in which values of attributes may be expressed by negation of some values or by a value subset of the attribute domain.
Data from which rules are induced are usually presented in a form similar to a table in which cases (or examples) are labels (or names) for rows and variables are labeled as attributes and a decision. We will restrict our attention to rule induction which belongs to supervised learning: all cases are preclassified by an expert. In different words, the decision value is assigned by an expert to each case. Attributes are independent variables and the decision is a dependent variable.
- QUOTE: Rule induction is one of the most important techniques of machine learning. Since regularities hidden in data are frequently expressed in terms of rules, rule induction is one of the fundamental tools of Data Mining at the same time. Usually rules are expressions of the form
1999
- (Zaiane, 1999) ⇒ Osmar Zaiane. (1999). “Glossary of Data Mining Terms." University of Alberta, Computing Science CMPUT-690: Principles of Knowledge Discovery in Databases.
- QUOTE: Rule Induction: The extraction of useful if-then rules from data based on statistical significance.