Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
Statistical relational learning
open-in-new
<p>Statistical relational learning (SRL) is a subdiscipline of <a href="/facts/Artificial_intelligence/lJGauQwX">artificial intelligence</a> and <a href="/facts/Machine_learning/e0w0XJTu">machine learning</a> that is concerned with <a href="/facts/Domain_model/rSxm7s5a">domain models</a> that exhibit both <a href="/facts/Uncertainty/VM9pnGvk">uncertainty</a> (which can be dealt with using statistical methods) and complex, <a href="/facts/Relation_(mathematics)/HjblDaMy">relational</a> structure. Typically, the <a href="/facts/Knowledge_representation/9lnzyILD">knowledge representation</a> formalisms developed in SRL use (a subset of) <a href="/facts/First-order_logic/lcISqWIg">first-order logic</a> to describe relational properties of a domain in a general manner (<a href="/facts/Universal_quantification/agNmvJKN">universal quantification</a>) and draw upon <a href="/facts/Probabilistic_graphical_model/XxfmKhmM">probabilistic graphical models</a> (such as <a href="/facts/Bayesian_network/Ry31vq6T">Bayesian networks</a> or <a href="/facts/Markov_network/DJazwaeP">Markov networks</a>) to model the uncertainty; some also build upon the methods of <a href="/facts/Inductive_logic_programming/gKc9Nxq4">inductive logic programming</a>. Significant contributions to the field have been made since the late 1990s. </p><p>As is evident from the characterization above, the field is not strictly limited to learning aspects; it is equally concerned with <a href="/facts/Semantic_reasoner/rXkm48cY">reasoning</a> (specifically <a href="/facts/Statistical_inference/sJLjubxm">probabilistic inference</a>) and <a href="/facts/Knowledge_representation/9lnzyILD">knowledge representation</a>. Therefore, alternative terms that reflect the main foci of the field include <i>statistical relational learning and reasoning</i> (emphasizing the importance of reasoning) and <i>first-order probabilistic languages</i> (emphasizing the key properties of the languages with which models are represented). Another term that is sometimes used in the literature is <i>relational machine learning</i> (RML). </p>