Understanding, Explanation, and Active Inference

While machine learning techniques have been transformative in solving a range of problems, an important challenge is to understand why they arrive at the decisions they output. Some have argued that this necessitates augmenting machine intelligence with understanding such that, when queried, a machi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thomas Parr, Giovanni Pezzulo
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	active inference explainable AI insight decision making generative model understanding Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/9d11f3a3f9a5462085c8de59506623cc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d11f3a3f9a5462085c8de59506623cc
record_format	dspace
spelling	oai:doaj.org-article:9d11f3a3f9a5462085c8de59506623cc2021-11-05T14:23:27ZUnderstanding, Explanation, and Active Inference1662-513710.3389/fnsys.2021.772641https://doaj.org/article/9d11f3a3f9a5462085c8de59506623cc2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnsys.2021.772641/fullhttps://doaj.org/toc/1662-5137While machine learning techniques have been transformative in solving a range of problems, an important challenge is to understand why they arrive at the decisions they output. Some have argued that this necessitates augmenting machine intelligence with understanding such that, when queried, a machine is able to explain its behaviour (i.e., explainable AI). In this article, we address the issue of machine understanding from the perspective of active inference. This paradigm enables decision making based upon a model of how data are generated. The generative model contains those variables required to explain sensory data, and its inversion may be seen as an attempt to explain the causes of these data. Here we are interested in explanations of one’s own actions. This implies a deep generative model that includes a model of the world, used to infer policies, and a higher-level model that attempts to predict which policies will be selected based upon a space of hypothetical (i.e., counterfactual) explanations—and which can subsequently be used to provide (retrospective) explanations about the policies pursued. We illustrate the construct validity of this notion of understanding in relation to human understanding by highlighting the similarities in computational architecture and the consequences of its dysfunction.Thomas ParrGiovanni PezzuloFrontiers Media S.A.articleactive inferenceexplainable AIinsightdecision makinggenerative modelunderstandingNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Systems Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	active inference explainable AI insight decision making generative model understanding Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	active inference explainable AI insight decision making generative model understanding Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Thomas Parr Giovanni Pezzulo Understanding, Explanation, and Active Inference
description	While machine learning techniques have been transformative in solving a range of problems, an important challenge is to understand why they arrive at the decisions they output. Some have argued that this necessitates augmenting machine intelligence with understanding such that, when queried, a machine is able to explain its behaviour (i.e., explainable AI). In this article, we address the issue of machine understanding from the perspective of active inference. This paradigm enables decision making based upon a model of how data are generated. The generative model contains those variables required to explain sensory data, and its inversion may be seen as an attempt to explain the causes of these data. Here we are interested in explanations of one’s own actions. This implies a deep generative model that includes a model of the world, used to infer policies, and a higher-level model that attempts to predict which policies will be selected based upon a space of hypothetical (i.e., counterfactual) explanations—and which can subsequently be used to provide (retrospective) explanations about the policies pursued. We illustrate the construct validity of this notion of understanding in relation to human understanding by highlighting the similarities in computational architecture and the consequences of its dysfunction.
format	article
author	Thomas Parr Giovanni Pezzulo
author_facet	Thomas Parr Giovanni Pezzulo
author_sort	Thomas Parr
title	Understanding, Explanation, and Active Inference
title_short	Understanding, Explanation, and Active Inference
title_full	Understanding, Explanation, and Active Inference
title_fullStr	Understanding, Explanation, and Active Inference
title_full_unstemmed	Understanding, Explanation, and Active Inference
title_sort	understanding, explanation, and active inference
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/9d11f3a3f9a5462085c8de59506623cc
work_keys_str_mv	AT thomasparr understandingexplanationandactiveinference AT giovannipezzulo understandingexplanationandactiveinference
_version_	1718444245384167424

Understanding, Explanation, and Active Inference

Ejemplares similares