Ciência-IUL
Comunicações
Descrição Detalhada da Comunicação
Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN)
Título Evento
CIENCIA 2019 Encontro com a Ciencia e Tecnologia em Portugal
Ano (publicação definitiva)
2019
Língua
Português
País
Portugal
Mais Informação
Web of Science®
Esta publicação não está indexada na Web of Science®
Scopus
Google Scholar
Esta publicação não está indexada no Google Scholar
Abstract/Resumo
Some Deep Neural Networks (DNN) have what we
call lanes, or they can be reorganized as such. Lanes are paths
in the network which are data-independent and typically learn
different features or add resilience to the network. Given their
data-independence, lanes are amenable for parallel processing.
The Multi-lane CapsNet (MLCN) is a proposed reorganization
of the Capsule Network which is shown to achieve better accuracy
while bringing highly-parallel lanes. However, the efficiency and
scalability of MLCN had not been systematically examined.
In this work, we study the MLCN network with multiple
GPUs finding that it is 2x more efficient than the original
CapsNet when using model-parallelism. Further, we present the
load balancing problem of distributing heterogeneous lanes in
homogeneous or heterogeneous accelerators and show that a
simple greedy heuristic can be almost 50% faster than a na¨ıve
random approach.
Agradecimentos/Acknowledgements
--
Palavras-chave
Classificação Fields of Science and Technology
- Ciências da Computação e da Informação - Ciências Naturais