Algorithmic probability (original) (raw)
アルゴリズム的情報理論において、ソロモノフのアルゴリズム的確率とはある観察にたいし事前確率を割り当てる数学的方法である。理論的には、その事前確率は普遍的である。帰納的推論の理論やアルゴリズムの解析などに使われている。計算可能ではなく、近似できるのみである。
| Property | Value |
|---|---|
| dbo:abstract | In algorithmic information theory, algorithmic probability, also known as Solomonoff probability, is a mathematical method of assigning a prior probability to a given observation. It was invented by Ray Solomonoff in the 1960s. It is used in inductive inference theory and analyses of algorithms. In his general theory of inductive inference, Solomonoff uses the method together with Bayes' rule to obtain probabilities of prediction for an algorithm's future outputs. In the mathematical formalism used, the observations have the form of finite binary strings viewed as outputs of Turing machines, and the universal prior is a probability distribution over the set of finite binary strings calculated from a probability distribution over programs (that is, inputs to a universal Turing machine). The prior is universal in theTuring-computability sense, i.e. no string has zero probability. It is not computable, but it can be approximated. (en) En théorie algorithmique de l'information, la probabilité algorithmique, aussi connue comme probabilité de Solomonoff, est une méthode permettant d’assigner une probabilité à une observation donnée. Il a été inventé par Ray Solomonoff dans les années 1960. Elle est utilisée dans la théorie de l'inférence inductive et dans l'analyse des algorithmes. En particulier, dans sa , Solomonoff utilise une telle formulation pour exprimer la probabilité a priori dans la formule de Bayes. Dans le formalisme mathématique utilisé, les observations se présentent sous la forme de chaînes binaires finies et l'a priori universel est une distribution de probabilité sur l'ensemble des chaînes binaires finies. Cet a priori est universel dans au sens de théorie de la calculabilité, c'est-à-dire qu'aucune chaîne n'a une probabilité nulle. Ce n'est pas calculable, mais on peut en faire une approximation. (fr) アルゴリズム的情報理論において、ソロモノフのアルゴリズム的確率とはある観察にたいし事前確率を割り当てる数学的方法である。理論的には、その事前確率は普遍的である。帰納的推論の理論やアルゴリズムの解析などに使われている。計算可能ではなく、近似できるのみである。 (ja) |
| dbo:wikiPageExternalLink | http://www.mdpi.com/1099-4300/13/6/1076/htm http://world.std.com/~rjs/publications/pubs.html http://scholarpedia.org/article/Algorithmic_probability |
| dbo:wikiPageID | 402688 (xsd:integer) |
| dbo:wikiPageLength | 8999 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID | 1098246192 (xsd:integer) |
| dbo:wikiPageWikiLink | dbr:Bayesian_inference dbr:Scholarpedia dbr:Algorithmic_information_theory dbc:Algorithmic_information_theory dbc:Probability_interpretations dbr:Inductive_probability dbr:Information-based_complexity dbc:Artificial_intelligence dbr:Computable_function dbr:Epicurus dbr:Andrey_Kolmogorov dbr:Leonid_Levin dbr:Kolmogorov_complexity dbr:Probability dbr:Karl_Popper dbr:Ray_Solomonoff dbr:Solomonoff's_theory_of_inductive_inference dbr:Turing_machine dbr:Universal_Turing_machine dbr:Universality_(philosophy) dbr:Occam's_razor dbr:Bayes'_rule dbr:Inductive_inference dbr:Universal_prior |
| dbp:date | September 2015 (en) |
| dbp:reason | According to his wikipedia article, 'Popper is known for his rejection of the classical inductivist views on the scientific method'. Consequently, he didn't give an 'inductive inference theory'. (en) |
| dbp:wikiPageUsesTemplate | dbt:Examples dbt:Citation_needed dbt:Clarify dbt:Reflist |
| dcterms:subject | dbc:Algorithmic_information_theory dbc:Probability_interpretations dbc:Artificial_intelligence |
| gold:hypernym | dbr:Method |
| rdf:type | dbo:Software yago:Abstraction100002137 yago:Cognition100023271 yago:Content105809192 yago:Interpretation105928513 yago:PsychologicalFeature100023100 yago:Representation105926676 yago:WikicatProbabilityInterpretations |
| rdfs:comment | アルゴリズム的情報理論において、ソロモノフのアルゴリズム的確率とはある観察にたいし事前確率を割り当てる数学的方法である。理論的には、その事前確率は普遍的である。帰納的推論の理論やアルゴリズムの解析などに使われている。計算可能ではなく、近似できるのみである。 (ja) In algorithmic information theory, algorithmic probability, also known as Solomonoff probability, is a mathematical method of assigning a prior probability to a given observation. It was invented by Ray Solomonoff in the 1960s. It is used in inductive inference theory and analyses of algorithms. In his general theory of inductive inference, Solomonoff uses the method together with Bayes' rule to obtain probabilities of prediction for an algorithm's future outputs. (en) En théorie algorithmique de l'information, la probabilité algorithmique, aussi connue comme probabilité de Solomonoff, est une méthode permettant d’assigner une probabilité à une observation donnée. Il a été inventé par Ray Solomonoff dans les années 1960. Elle est utilisée dans la théorie de l'inférence inductive et dans l'analyse des algorithmes. En particulier, dans sa , Solomonoff utilise une telle formulation pour exprimer la probabilité a priori dans la formule de Bayes. (fr) |
| rdfs:label | Algorithmic probability (en) Probabilité algorithmique (fr) アルゴリズム的確率 (ja) |
| owl:sameAs | freebase:Algorithmic probability yago-res:Algorithmic probability wikidata:Algorithmic probability dbpedia-fr:Algorithmic probability dbpedia-ja:Algorithmic probability https://global.dbpedia.org/id/4NxmT |
| prov:wasDerivedFrom | wikipedia-en:Algorithmic_probability?oldid=1098246192&ns=0 |
| foaf:isPrimaryTopicOf | wikipedia-en:Algorithmic_probability |
| is dbo:wikiPageDisambiguates of | dbr:Algorithmic |
| is dbo:wikiPageWikiLink of | dbr:List_of_computability_and_complexity_topics dbr:Algorithmic_information_theory dbr:Peter_Gacs dbr:Universality_probability dbr:Index_of_robotics_articles dbr:Inductive_probability dbr:Invariance_theorem dbr:General_semantics dbr:Glossary_of_artificial_intelligence dbr:Leonid_Levin dbr:Kolmogorov_complexity dbr:Prior_probability dbr:Randomness dbr:ALP dbr:Ray_Solomonoff dbr:Solomonoff's_theory_of_inductive_inference dbr:Inductive_reasoning dbr:Information_theory dbr:Algorithmic dbr:Minimum_description_length dbr:Minimum_message_length dbr:Occam's_razor dbr:Simplicity_theory dbr:Outline_of_artificial_intelligence dbr:Outline_of_computer_programming |
| is foaf:primaryTopic of | wikipedia-en:Algorithmic_probability |