Exportar Publicação

M.Breternitz (2019). Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN) . International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) .

M. B. Jr.,  "Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN) ", in Int. Symp. on Computer Architecture and High Performance Computing (SBAC-PAD) , 2019

@null{jr.2019_1728918782751,
	year = "2019",
	url = "https://ciencia.iscte-iul.pt/publications/efficiency-and-scalability-of-multi-lane-capsule-networks-mlcn-/61916?lang=en"
}

TY  - GEN
TI  - Efficiency and Scalability of Multi-Lane Capsule Networks (MLCN) 
T2  - International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) 
AU  - M.Breternitz
PY  - 2019
DO  - 10.1109/SBAC-PAD.2019.00034
UR  - https://ciencia.iscte-iul.pt/publications/efficiency-and-scalability-of-multi-lane-capsule-networks-mlcn-/61916?lang=en
AB  - 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   origina lCapsNet 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  naıve random  approach
ER  -