Brain-Inspired Hardware Solutions for Inference in Bayesian Networks

The implementation of inference (i.e., computing posterior probabilities) in Bayesian networks using a conventional computing paradigm turns out to be inefficient in terms of energy, time, and space, due to the substantial resources required by floating-point operations. A departure from conventiona...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Leila Bagheriye, Johan Kwisthout
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	brain inspired computing Bayesian inference spiking neural networks (SNN) nonvolatile stochastic computing Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/17df76067bbf494885b59d072926076c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:17df76067bbf494885b59d072926076c
record_format	dspace
spelling	oai:doaj.org-article:17df76067bbf494885b59d072926076c2021-12-02T11:23:48ZBrain-Inspired Hardware Solutions for Inference in Bayesian Networks1662-453X10.3389/fnins.2021.728086https://doaj.org/article/17df76067bbf494885b59d072926076c2021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fnins.2021.728086/fullhttps://doaj.org/toc/1662-453XThe implementation of inference (i.e., computing posterior probabilities) in Bayesian networks using a conventional computing paradigm turns out to be inefficient in terms of energy, time, and space, due to the substantial resources required by floating-point operations. A departure from conventional computing systems to make use of the high parallelism of Bayesian inference has attracted recent attention, particularly in the hardware implementation of Bayesian networks. These efforts lead to several implementations ranging from digital circuits, mixed-signal circuits, to analog circuits by leveraging new emerging nonvolatile devices. Several stochastic computing architectures using Bayesian stochastic variables have been proposed, from FPGA-like architectures to brain-inspired architectures such as crossbar arrays. This comprehensive review paper discusses different hardware implementations of Bayesian networks considering different devices, circuits, and architectures, as well as a more futuristic overview to solve existing hardware implementation problems.Leila BagheriyeJohan KwisthoutFrontiers Media S.A.articlebrain inspired computingBayesian inferencespiking neural networks (SNN)nonvolatilestochastic computingNeurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENFrontiers in Neuroscience, Vol 15 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	brain inspired computing Bayesian inference spiking neural networks (SNN) nonvolatile stochastic computing Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	brain inspired computing Bayesian inference spiking neural networks (SNN) nonvolatile stochastic computing Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Leila Bagheriye Johan Kwisthout Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
description	The implementation of inference (i.e., computing posterior probabilities) in Bayesian networks using a conventional computing paradigm turns out to be inefficient in terms of energy, time, and space, due to the substantial resources required by floating-point operations. A departure from conventional computing systems to make use of the high parallelism of Bayesian inference has attracted recent attention, particularly in the hardware implementation of Bayesian networks. These efforts lead to several implementations ranging from digital circuits, mixed-signal circuits, to analog circuits by leveraging new emerging nonvolatile devices. Several stochastic computing architectures using Bayesian stochastic variables have been proposed, from FPGA-like architectures to brain-inspired architectures such as crossbar arrays. This comprehensive review paper discusses different hardware implementations of Bayesian networks considering different devices, circuits, and architectures, as well as a more futuristic overview to solve existing hardware implementation problems.
format	article
author	Leila Bagheriye Johan Kwisthout
author_facet	Leila Bagheriye Johan Kwisthout
author_sort	Leila Bagheriye
title	Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
title_short	Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
title_full	Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
title_fullStr	Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
title_full_unstemmed	Brain-Inspired Hardware Solutions for Inference in Bayesian Networks
title_sort	brain-inspired hardware solutions for inference in bayesian networks
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/17df76067bbf494885b59d072926076c
work_keys_str_mv	AT leilabagheriye braininspiredhardwaresolutionsforinferenceinbayesiannetworks AT johankwisthout braininspiredhardwaresolutionsforinferenceinbayesiannetworks
_version_	1718395924289421312

Brain-Inspired Hardware Solutions for Inference in Bayesian Networks

Ejemplares similares