Cargando…

Neural Information Squeezer for Causal Emergence

Conventional studies of causal emergence have revealed that stronger causality can be obtained on the macro-level than the micro-level of the same Markovian dynamical systems if an appropriate coarse-graining strategy has been conducted on the micro-states. However, identifying this emergent causali...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Jiang, Liu, Kaiwei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9858212/
https://www.ncbi.nlm.nih.gov/pubmed/36673167
http://dx.doi.org/10.3390/e25010026
_version_ 1784874042614874112
author Zhang, Jiang
Liu, Kaiwei
author_facet Zhang, Jiang
Liu, Kaiwei
author_sort Zhang, Jiang
collection PubMed
description Conventional studies of causal emergence have revealed that stronger causality can be obtained on the macro-level than the micro-level of the same Markovian dynamical systems if an appropriate coarse-graining strategy has been conducted on the micro-states. However, identifying this emergent causality from data is still a difficult problem that has not been solved because the appropriate coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-level dynamics, as well as identify causal emergence directly from time series data. By using invertible neural network, we can decompose any coarse-graining strategy into two separate procedures: information conversion and information discarding. In this way, we can not only exactly control the width of the information channel, but also can derive some important properties analytically. We also show how our framework can extract the coarse-graining functions and the dynamics on different levels, as well as identify causal emergence from the data on several exampled systems.
format Online
Article
Text
id pubmed-9858212
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98582122023-01-21 Neural Information Squeezer for Causal Emergence Zhang, Jiang Liu, Kaiwei Entropy (Basel) Article Conventional studies of causal emergence have revealed that stronger causality can be obtained on the macro-level than the micro-level of the same Markovian dynamical systems if an appropriate coarse-graining strategy has been conducted on the micro-states. However, identifying this emergent causality from data is still a difficult problem that has not been solved because the appropriate coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-level dynamics, as well as identify causal emergence directly from time series data. By using invertible neural network, we can decompose any coarse-graining strategy into two separate procedures: information conversion and information discarding. In this way, we can not only exactly control the width of the information channel, but also can derive some important properties analytically. We also show how our framework can extract the coarse-graining functions and the dynamics on different levels, as well as identify causal emergence from the data on several exampled systems. MDPI 2022-12-23 /pmc/articles/PMC9858212/ /pubmed/36673167 http://dx.doi.org/10.3390/e25010026 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Jiang
Liu, Kaiwei
Neural Information Squeezer for Causal Emergence
title Neural Information Squeezer for Causal Emergence
title_full Neural Information Squeezer for Causal Emergence
title_fullStr Neural Information Squeezer for Causal Emergence
title_full_unstemmed Neural Information Squeezer for Causal Emergence
title_short Neural Information Squeezer for Causal Emergence
title_sort neural information squeezer for causal emergence
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9858212/
https://www.ncbi.nlm.nih.gov/pubmed/36673167
http://dx.doi.org/10.3390/e25010026
work_keys_str_mv AT zhangjiang neuralinformationsqueezerforcausalemergence
AT liukaiwei neuralinformationsqueezerforcausalemergence