]> 2008/06/10 OpenCyc Knowledge Base Copyright© 2001-2008 Cycorp, Inc., http://www.cyc.com/, Austin, TX, USA This file contains an OWL representation of information contained in the OpenCyc Knowledge Base. The content of this OWL file is licensed under the Creative Commons Attribution 3.0 license whose text can be found at http://creativecommons.org/licenses/by/3.0/legalcode. The content of this OWL file, including the OpenCyc content it represents, constitutes the "Work" referred to in the Creative Commons license. The terms of this license equally apply to, without limitation, renamings and other logically equivalent reformulations of the content of this OWL file (or portions thereof) in any natural or formal language, as well as to derivations of this content or inclusion of it in other ontologies. externalID A unique, language-neutral, variable-sized identifier for a concept that can be used to refer unambiguously to that concept across OWL exports or across Cyc inference engines. label A natural-language representation for a concept that is both human readable and readable by the Cyc inference engine. These terms are not guaranteed to refer to the same concept across time but are guaranteed to be consistent within a particular OWL export. Use 'cycAnnot:externalID' for unambiguously referring to a concept across OWL exports or across Cyc inference engines. The collection of all Bayesian Networks intended for probability reasoning. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a network of nodes in which the nodes are random variables that each typically represent the likelihood of a proposition being true (expressed as a real number between zero and one, where zero means certainly false and one means certainly true). See <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtSZipwpEbGdrcN5Y29ycA" class="cyc_term">bayesNetOfMicrotheory</a>. Each <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> interconnects a set of propositions (or symbols associated with propositions) together forming a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> in which the links (the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> link) represent a probabilistic conditional dependence between the directly linked nodes. Such a network may be established by asserting (or concluding) <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> predications linking pairs of propositions. There is a 'closed-world assumption' for every <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>, in that pairs of propositions not explicitly linked with <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> are assumed to be not linked. In addition, a node is <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvX2CRJwpEbGdrcN5Y29ycA" class="cyc_term">conditionallyIndependentSentences</a> the truth values of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (and no other nodes) - from all nodes other than its 'descendants' in the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a representation of the entire (strictly positive) joint probability distribution over the random variables. The <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvi7c9JwpEbGdrcN5Y29ycA" class="cyc_term">derivedProbability</a> of a node can be calculated from the probabilities of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s. (There are always one or more 'source' nodes with no <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s.) Theoretically, viewed as evidential links based on the joint probability distribution, the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> links are bidirectional. The direction of the links is obtained formally due to an asymmetry between 'parents' and 'children': the truth of a node induces a conditional dependence among its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (the 'explaining away' effect), which does not seem to apply to its Bayesian 'child' nodes. Most Bayesian network theorists consider that the directions on the links correspond to the direction of causal influence, and hence to the direction of time. The name 'Bayesian' is due to the Reverend Thomas Bayes, whose inversion rule was published posthumously in 1763, and later developed by Laplace. Bayesian Networks were devised chiefly by Judea Pearl in the 1980s. BayesNet bayes net http://en.wikipedia.org/wiki/Bayesian_network bayes nets CarEngineStarting Car Engine Starting The collection of all Bayesian Networks intended for probability reasoning. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a network of nodes in which the nodes are random variables that each typically represent the likelihood of a proposition being true (expressed as a real number between zero and one, where zero means certainly false and one means certainly true). See <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtSZipwpEbGdrcN5Y29ycA" class="cyc_term">bayesNetOfMicrotheory</a>. Each <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> interconnects a set of propositions (or symbols associated with propositions) together forming a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> in which the links (the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> link) represent a probabilistic conditional dependence between the directly linked nodes. Such a network may be established by asserting (or concluding) <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> predications linking pairs of propositions. There is a 'closed-world assumption' for every <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>, in that pairs of propositions not explicitly linked with <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> are assumed to be not linked. In addition, a node is <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvX2CRJwpEbGdrcN5Y29ycA" class="cyc_term">conditionallyIndependentSentences</a> the truth values of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (and no other nodes) - from all nodes other than its 'descendants' in the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a representation of the entire (strictly positive) joint probability distribution over the random variables. The <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvi7c9JwpEbGdrcN5Y29ycA" class="cyc_term">derivedProbability</a> of a node can be calculated from the probabilities of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s. (There are always one or more 'source' nodes with no <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s.) Theoretically, viewed as evidential links based on the joint probability distribution, the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> links are bidirectional. The direction of the links is obtained formally due to an asymmetry between 'parents' and 'children': the truth of a node induces a conditional dependence among its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (the 'explaining away' effect), which does not seem to apply to its Bayesian 'child' nodes. Most Bayesian network theorists consider that the directions on the links correspond to the direction of causal influence, and hence to the direction of time. The name 'Bayesian' is due to the Reverend Thomas Bayes, whose inversion rule was published posthumously in 1763, and later developed by Laplace. Bayesian Networks were devised chiefly by Judea Pearl in the 1980s. BayesNet bayes net The collection of all Bayesian Networks intended for probability reasoning. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a network of nodes in which the nodes are random variables that each typically represent the likelihood of a proposition being true (expressed as a real number between zero and one, where zero means certainly false and one means certainly true). See <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtSZipwpEbGdrcN5Y29ycA" class="cyc_term">bayesNetOfMicrotheory</a>. Each <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> interconnects a set of propositions (or symbols associated with propositions) together forming a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> in which the links (the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> link) represent a probabilistic conditional dependence between the directly linked nodes. Such a network may be established by asserting (or concluding) <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> predications linking pairs of propositions. There is a 'closed-world assumption' for every <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>, in that pairs of propositions not explicitly linked with <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> are assumed to be not linked. In addition, a node is <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvX2CRJwpEbGdrcN5Y29ycA" class="cyc_term">conditionallyIndependentSentences</a> the truth values of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (and no other nodes) - from all nodes other than its 'descendants' in the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a representation of the entire (strictly positive) joint probability distribution over the random variables. The <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvi7c9JwpEbGdrcN5Y29ycA" class="cyc_term">derivedProbability</a> of a node can be calculated from the probabilities of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s. (There are always one or more 'source' nodes with no <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s.) Theoretically, viewed as evidential links based on the joint probability distribution, the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> links are bidirectional. The direction of the links is obtained formally due to an asymmetry between 'parents' and 'children': the truth of a node induces a conditional dependence among its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (the 'explaining away' effect), which does not seem to apply to its Bayesian 'child' nodes. Most Bayesian network theorists consider that the directions on the links correspond to the direction of causal influence, and hence to the direction of time. The name 'Bayesian' is due to the Reverend Thomas Bayes, whose inversion rule was published posthumously in 1763, and later developed by Laplace. Bayesian Networks were devised chiefly by Judea Pearl in the 1980s. BayesNet bayes net DirectedAcyclicGraph Directed Acyclic Graph The collection of all those <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvrPfJpwpEbGdrcN5Y29ycA" class="cyc_term">DirectedGraph</a>s (node-and-link structures in which each link has one direction) each of which has no directed cycle in it. This is the intersection of <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvrPfJpwpEbGdrcN5Y29ycA" class="cyc_term">DirectedGraph</a> and <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvdnP8ZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicPathSystem</a> (which is the same as the intersection of <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rviabPZwpEbGdrcN5Y29ycA" class="cyc_term">SimpleGraph_GraphTheoretic</a> and <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvdnP8ZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicPathSystem</a>). A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> is often used as a representation of a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rwTWq1ZwpEbGdrcN5Y29ycA" class="cyc_term">PartialOrdering</a>. Pretty String (<a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rwLSVCpwpEbGdrcN5Y29ycA" class="cyc_term">prettyString</a> TERM STRING) means that STRING is the English word or expression (sequence of words) commonly used to refer to TERM. The predicate <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rwLSVCpwpEbGdrcN5Y29ycA" class="cyc_term">prettyString</a> is used by the code which generates CycL to English paraphrases, but its applicability is not restricted to this use. prettyString Probability-Topic probability-topic A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rAmoSCGJbQdiSXZJvYiNhkQ" class="cyc_term">CycVocabularyTopic</a> and a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rtGXkHpNaEdqAAAACs0uFOQ" class="cyc_term">KBDependentCollection</a>. The collection of all Bayesian Networks intended for probability reasoning. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a network of nodes in which the nodes are random variables that each typically represent the likelihood of a proposition being true (expressed as a real number between zero and one, where zero means certainly false and one means certainly true). See <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtSZipwpEbGdrcN5Y29ycA" class="cyc_term">bayesNetOfMicrotheory</a>. Each <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> interconnects a set of propositions (or symbols associated with propositions) together forming a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> in which the links (the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> link) represent a probabilistic conditional dependence between the directly linked nodes. Such a network may be established by asserting (or concluding) <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> predications linking pairs of propositions. There is a 'closed-world assumption' for every <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>, in that pairs of propositions not explicitly linked with <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> are assumed to be not linked. In addition, a node is <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvX2CRJwpEbGdrcN5Y29ycA" class="cyc_term">conditionallyIndependentSentences</a> the truth values of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (and no other nodes) - from all nodes other than its 'descendants' in the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a representation of the entire (strictly positive) joint probability distribution over the random variables. The <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvi7c9JwpEbGdrcN5Y29ycA" class="cyc_term">derivedProbability</a> of a node can be calculated from the probabilities of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s. (There are always one or more 'source' nodes with no <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s.) Theoretically, viewed as evidential links based on the joint probability distribution, the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> links are bidirectional. The direction of the links is obtained formally due to an asymmetry between 'parents' and 'children': the truth of a node induces a conditional dependence among its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (the 'explaining away' effect), which does not seem to apply to its Bayesian 'child' nodes. Most Bayesian network theorists consider that the directions on the links correspond to the direction of causal influence, and hence to the direction of time. The name 'Bayesian' is due to the Reverend Thomas Bayes, whose inversion rule was published posthumously in 1763, and later developed by Laplace. Bayesian Networks were devised chiefly by Judea Pearl in the 1980s. BayesNet bayes net The collection of all Bayesian Networks intended for probability reasoning. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a network of nodes in which the nodes are random variables that each typically represent the likelihood of a proposition being true (expressed as a real number between zero and one, where zero means certainly false and one means certainly true). See <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtSZipwpEbGdrcN5Y29ycA" class="cyc_term">bayesNetOfMicrotheory</a>. Each <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> interconnects a set of propositions (or symbols associated with propositions) together forming a <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvtXKWZwpEbGdrcN5Y29ycA" class="cyc_term">DirectedAcyclicGraph</a> in which the links (the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> link) represent a probabilistic conditional dependence between the directly linked nodes. Such a network may be established by asserting (or concluding) <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> predications linking pairs of propositions. There is a 'closed-world assumption' for every <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>, in that pairs of propositions not explicitly linked with <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> are assumed to be not linked. In addition, a node is <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvX2CRJwpEbGdrcN5Y29ycA" class="cyc_term">conditionallyIndependentSentences</a> the truth values of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (and no other nodes) - from all nodes other than its 'descendants' in the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a>. A <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvhSzKJwpEbGdrcN5Y29ycA" class="cyc_term">BayesNet</a> is a representation of the entire (strictly positive) joint probability distribution over the random variables. The <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvi7c9JwpEbGdrcN5Y29ycA" class="cyc_term">derivedProbability</a> of a node can be calculated from the probabilities of its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s. (There are always one or more 'source' nodes with no <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s.) Theoretically, viewed as evidential links based on the joint probability distribution, the <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a> links are bidirectional. The direction of the links is obtained formally due to an asymmetry between 'parents' and 'children': the truth of a node induces a conditional dependence among its <a href="http://sw.opencyc.org/2008/06/10/concept/Mx4rvbvRRJwpEbGdrcN5Y29ycA" class="cyc_term">bayesParent</a>s (the 'explaining away' effect), which does not seem to apply to its Bayesian 'child' nodes. Most Bayesian network theorists consider that the directions on the links correspond to the direction of causal influence, and hence to the direction of time. The name 'Bayesian' is due to the Reverend Thomas Bayes, whose inversion rule was published posthumously in 1763, and later developed by Laplace. Bayesian Networks were devised chiefly by Judea Pearl in the 1980s. BayesNet bayes net