Zobrazit v EDS

22. Correlation and Causality

Uloženo v:
Podrobná bibliografie
Název: 22. Correlation and Causality
Autoři: García Pedraza, Rubén
Informace o vydavateli: Zenodo, 2025.
Rok vydání: 2025
Témata: Artificial intelligence, Artificial Intelligence/legislation & jurisprudence, Artificial Intelligence/statistics & numerical data, Artificial Intelligence/economics, Artificial Intelligence/ethics, Artificial Intelligence/standards, Watson, Artificial Research by Deduction, Artificial Intelligence/supply & distribution, Artificial Intelligence/history, Artificial Intelligence, Artificial Intelligence/classification, A then possibly B, Artificial Intelligence/trends, Skinner
Popis: The true importance of this post on our blog Impossible Probability is the fact that it offers a clear definition of how Artificial Research by Deduction must work by the time the first Specific Artificial Intelligences by Deduction are built. In essence, the mechanism is quite simple: programs working by deduction should be able to identify data from the matrix and match that data with the correct equation capable of explaining its behaviour. As soon as our machine is able to identify which equation corresponds to the behaviour of a data sample, what our machine is doing is forming an empirical hypothesis. At this stage, the machine must also be able to identify possible correlations, causes and effects, or any other mathematical or cryptographic relation or pattern. Once the machine is able to carry out this task, this initial mathematical proposition is considered an empirical hypothesis to be tested. In order to test the hypothesis, our deductive program must be able to collect data from the matrix to verify it, and if it proves to be correct, then the hypothesis is considered rational and is stored in the database of rational hypotheses, also called the Rational Truth. This forms the first stage of the Modelling System, where hypotheses may later be modelled after passing the required assessments, if necessary. In essence, the entire logic behind our program for Artificial Research by Deduction is what we summarised in this post, written for our blog Impossible Probability on 19 April 2014.
Druh dokumentu: Part of book or chapter of book
Jazyk: English
DOI: 10.5281/zenodo.17159175
DOI: 10.5281/zenodo.17159174
Rights: CC BY
Přístupové číslo: edsair.doi.dedup.....1b482f365f404fcf2d3241f2d1c16fd7
Databáze: OpenAIRE
Popis
Abstrakt:The true importance of this post on our blog Impossible Probability is the fact that it offers a clear definition of how Artificial Research by Deduction must work by the time the first Specific Artificial Intelligences by Deduction are built. In essence, the mechanism is quite simple: programs working by deduction should be able to identify data from the matrix and match that data with the correct equation capable of explaining its behaviour. As soon as our machine is able to identify which equation corresponds to the behaviour of a data sample, what our machine is doing is forming an empirical hypothesis. At this stage, the machine must also be able to identify possible correlations, causes and effects, or any other mathematical or cryptographic relation or pattern. Once the machine is able to carry out this task, this initial mathematical proposition is considered an empirical hypothesis to be tested. In order to test the hypothesis, our deductive program must be able to collect data from the matrix to verify it, and if it proves to be correct, then the hypothesis is considered rational and is stored in the database of rational hypotheses, also called the Rational Truth. This forms the first stage of the Modelling System, where hypotheses may later be modelled after passing the required assessments, if necessary. In essence, the entire logic behind our program for Artificial Research by Deduction is what we summarised in this post, written for our blog Impossible Probability on 19 April 2014.
DOI:10.5281/zenodo.17159175