A comparison of stochastic gradient MCMC using multi-core and GPU architectures

dc.contributor.author	Hernández, Sergio
dc.contributor.author	Valdés, José
dc.contributor.author	Valdenegro, Matias
dc.date.accessioned	2020-10-26T12:55:39Z
dc.date.available	2020-10-26T12:55:39Z
dc.date.issued	2020
dc.identifier.uri	http://repositorio.ucm.cl/handle/ucm/3120
dc.description.abstract	Deep learning models are traditionally used in big data scenarios. When there is not enough training data to fit a large model, transfer learning re-purpose the learned features from an existing model and re-train the lower layers for the new task. Bayesian inference techniques can be used to capture the uncertainty of the new model but it comes with a high computational cost. In this paper, the run time performance of an Stochastic Gradient Markov Chain Monte Carlo method using two different architectures is compared, namely GPU and multi-core CPU. As opposed to the widely usage of GPUs for deep learning, significant advantages from using modern CPU architectures.	es_CL
dc.language.iso	en	es_CL
dc.rights	Atribución-NoComercial-SinDerivadas 3.0 Chile	*
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/cl/	*
dc.source	2020 Congreso Estudiantil de Electrónica y Electricidad (INGELECTRA)	es_CL
dc.title	A comparison of stochastic gradient MCMC using multi-core and GPU architectures	es_CL
dc.type	Article	es_CL
dc.ucm.indexacion	Scopus	es_CL
dc.ucm.uri	ieeexplore.ieee.org/document/9087329/authors#authors	es_CL
dc.ucm.doi	doi.org/10.1109/INGELECTRA50225.2020.246962	es_CL

Ficheros en la publicación

Ficheros	Tamaño	Formato	Ver
No hay ficheros asociados a esta publicación.

Excepto si se señala otra cosa, la licencia de la publicación se describe como Atribución-NoComercial-SinDerivadas 3.0 Chile