Bayesian selection of grammar productions for the language of thought
Bayesian selection of grammar productions for the language of thought
Probabilistic proposals of Language of Thoughts (LoTs) can explain learning across different domains as statistical inference over a compositionally structured hypothesis space. While frameworks may differ on how a LoT may be implemented computationally, they all share the property that they are built from a set of atomic symbols and rules by which these symbols can be combined. In this work we show how the set of productions of a LoT grammar can be effectively selected from a broad repertoire of possible productions by an inferential process starting from experimental data. We then test this method in the language of geometry, a specific LoT model (Amalric et al., 2017). Finally, despite the fact of the geometrical LoT not being a universal (i.e. Turing-complete) language, we show an empirical relation between a sequence’s probability and its complexity consistent with the theoretical relationship for universal languages described by Levin’s Coding Theorem.
Romano S.、Sigman M.、Amalric M.、Dehaene S.、Figueria S.、Salles A.
Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computaci¨?n||CONICET-Universidad de Buenos Aires. Instituto de Investigaci¨?n en Ciencias de la Computaci¨?n (ICC)CONICET-Universidad Torcuato Di Tella. Laboratorio de NeurocienciaCognitive Neuroimaging Unit, CEA DSV/I2BM, INSERM, Universit¨| Paris-Sud, Universit¨| Paris-SaclayCognitive Neuroimaging Unit, CEA DSV/I2BM, INSERM, Universit¨| Paris-Sud, Universit¨| Paris-SaclayUniversidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computaci¨?n||CONICET-Universidad de Buenos Aires. Instituto de Investigaci¨?n en Ciencias de la Computaci¨?n (ICC)CONICET-Universidad de Buenos Aires. Instituto de C¨￠lculo (IC)
数学计算技术、计算机技术
Language of thoughtBayesian inferenceMinimal Description LengthCoding TheoremLanguage of geometryContext-free grammar
Romano S.,Sigman M.,Amalric M.,Dehaene S.,Figueria S.,Salles A..Bayesian selection of grammar productions for the language of thought[EB/OL].(2025-03-28)[2025-05-15].https://www.biorxiv.org/content/10.1101/141358.点此复制
评论