Weightless Neural Networks for Efficient Edge Inference

Autor: Susskind, Zachary, Arora, Aman, Miranda, Igor Dantas Dos Santos, Villon, Luis Armando Quintanilla, Katopodis, Rafael Fontella, de Araujo, Leandro Santiago, Dutra, Diego Leonel Cadette, Lima, Priscila Machado Vieira, Franca, Felipe Maia Galvao, Breternitz Jr., Mauricio, John, Lizy K.

Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. This is in contrast with Deep Neural Networks (DNNs), which use multiply-accumulate operations. State-of-the-art WNN architectures h

Externí odkaz: http://arxiv.org/abs/2203.01479

Dynamic Placement with Connectivity for RSNs based on a Primal-Dual Neural Network

Autor: Lima De Carvalho, Rafael, Zhong, Lunlong, França, Felipe Maia Galvão, Mora-Camino, Felix

Publikováno v: ESANN 2013, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
ESANN 2013, 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2013, Bruges, Belgium. pp 245-250

https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2013-62.pdf; International audience; The present work deals with the dynamic placement of a set of pursuers and a set of relay devices so that the mean distance to a set of moving targets is min

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c8654c44c62cb16624982214faeae90f
https://hal-enac.archives-ouvertes.fr/hal-01066624/document

Explorando a equivalência entre uma máquina química abstrata e computação dataflow

Autor: Mello Junior, Rui Rodrigues de

Publikováno v: Repositório Institucional da Diretoria do Patrimônio Histórico e Documentação da Marinha
Marinha do Brasil (MB)
instacron:MB

Atualmente, a busca por desempenho computacional, tanto em aplicações de computação científica quanto em aplicações de uso geral, aponta para a computação paralela como área de interesse para sobrepor as dificuldades encontradas nos paradig

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::cf823f4a554d68bb5e31760b8cfca7c6
https://www.repositorio.mar.mil.br/handle/ripcmb/845501

A differentiated proposal of three dimension i/o performance characterization model focusing on storage environments

Autor: Pioli Junior, Laercio

Publikováno v: Repositório Institucional da UFJF
Universidade Federal de Juiz de Fora (UFJF)
instacron:UFJF

O gargalo de E/S continua sendo um problema central em ambientes de alto desempenho. Os ambientes de computação em nuvem, computação de alto desempenho (HPC) e big data compartilham muitas dificuldades para fornecer dados em uma taxa de tempo des

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::8ed68606945e4d5a0ab676905ae86e62
https://repositorio.ufjf.br/jspui/handle/ufjf/11938

Computational methodology for the study of stellar moving groups

Autor: Nascimento, Josina Oliveira de

Publikováno v: Repositório Institucional da UFRJ
Universidade Federal do Rio de Janeiro (UFRJ)
instacron:UFRJ

Submitted by Paloma Arruda (palomaoliiveira75@gmail.com) on 2021-02-22T20:06:28Z No. of bitstreams: 1 JosinaOliveiraDoNascimento.pdf: 2054391 bytes, checksum: 38affffd0e8b7903944b9ed933eb82aa (MD5) Approved for entry into archive by Moreno Barros (mo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od______3056::c3d31de34e8ec9130a5f7415c46501b6