Bayesian validation of grammar productions for the language of thought
Probabilistic proposals of Language of Thoughts (LoTs) can explain learning across differ- ent 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 b...
Guardado en:
Autores principales: | , , , , , |
---|---|
Formato: | Documento de trabajo publishedVersion |
Lenguaje: | Inglés |
Publicado: |
2018
|
Materias: | |
Acceso en línea: | https://doi.org/10.1371/journal.pone.0200420 https://repositorio.utdt.edu/handle/20.500.13098/11219 |
Aporte de: |
id |
I57-R16320.500.13098-11219 |
---|---|
record_format |
dspace |
institution |
Universidad Torcuato Di Tella |
institution_str |
I-57 |
repository_str |
R-163 |
collection |
Repositorio Digital Universidad Torcuato Di Tella |
language |
Inglés |
orig_language_str_mv |
eng |
topic |
Gramática Lenguaje Teoría de la información Simetría Aprendizaje Lenguajes de programación Sintaxis Grammar Language Information theory Symmetry Learning Programming languages Syntax |
spellingShingle |
Gramática Lenguaje Teoría de la información Simetría Aprendizaje Lenguajes de programación Sintaxis Grammar Language Information theory Symmetry Learning Programming languages Syntax Romano, Sergio Salles, Alejo Amalric, Marie Deahene, Stanislas Sigman, Mariano Figueira, Santiago Bayesian validation of grammar productions for the language of thought |
description |
Probabilistic proposals of Language of Thoughts (LoTs) can explain learning across differ- ent 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 propose an extra validation step for the set of atomic productions defined by the experimenter. It starts by expanding the defined LoT grammar for the cognitive domain with a broader set of arbitrary productions and then uses Bayesian inference to prune the productions from the experimental data. The result allows the researcher to validate that the resulting grammar still matches the intuitive grammar cho- sen for the domain. We then test this method in the language of geometry, a specific LoT model for geometrical sequence learning. 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 uni- versal languages described by Levin’s Coding Theorem. |
format |
Documento de trabajo publishedVersion |
author |
Romano, Sergio Salles, Alejo Amalric, Marie Deahene, Stanislas Sigman, Mariano Figueira, Santiago |
author_facet |
Romano, Sergio Salles, Alejo Amalric, Marie Deahene, Stanislas Sigman, Mariano Figueira, Santiago |
author_sort |
Romano, Sergio |
title |
Bayesian validation of grammar productions for the language of thought |
title_short |
Bayesian validation of grammar productions for the language of thought |
title_full |
Bayesian validation of grammar productions for the language of thought |
title_fullStr |
Bayesian validation of grammar productions for the language of thought |
title_full_unstemmed |
Bayesian validation of grammar productions for the language of thought |
title_sort |
bayesian validation of grammar productions for the language of thought |
publishDate |
2018 |
url |
https://doi.org/10.1371/journal.pone.0200420 https://repositorio.utdt.edu/handle/20.500.13098/11219 |
work_keys_str_mv |
AT romanosergio bayesianvalidationofgrammarproductionsforthelanguageofthought AT sallesalejo bayesianvalidationofgrammarproductionsforthelanguageofthought AT amalricmarie bayesianvalidationofgrammarproductionsforthelanguageofthought AT deahenestanislas bayesianvalidationofgrammarproductionsforthelanguageofthought AT sigmanmariano bayesianvalidationofgrammarproductionsforthelanguageofthought AT figueirasantiago bayesianvalidationofgrammarproductionsforthelanguageofthought |
bdutipo_str |
Repositorios |
_version_ |
1764820542765924356 |