Redirigiendo al acceso original de articulo en 20 segundos...
Inicio  /  Future Internet  /  Vol: 11 Par: 10 (2019)  /  Artículo
ARTÍCULO
TITULO

Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices

Fabíola Martins Campos de Oliveira and Edson Borin    

Resumen

Billions of devices will compose the IoT system in the next few years, generating a huge amount of data. We can use fog computing to process these data, considering that there is the possibility of overloading the network towards the cloud. In this context, deep learning can treat these data, but the memory requirements of deep neural networks may prevent them from executing on a single resource-constrained device. Furthermore, their computational requirements may yield an unfeasible execution time. In this work, we propose Deep Neural Networks Partitioning for Constrained IoT Devices, a new algorithm to partition neural networks for efficient distributed execution. Our algorithm can optimize the neural network inference rate or the number of communications among devices. Additionally, our algorithm accounts appropriately for the shared parameters and biases of Convolutional Neural Networks. We investigate the inference rate maximization for the LeNet model in constrained setups. We show that the partitionings offered by popular machine learning frameworks such as TensorFlow or by the general-purpose framework METIS may produce invalid partitionings for very constrained setups. The results show that our algorithm can partition LeNet for all the proposed setups, yielding up to 38% more inferences per second than METIS.

 Artículos similares

       
 
M.H.J.P. Gunarathna, Kazuhito Sakai, Tamotsu Nakandakari, Kazuro Momii and M.K.N. Kumari    
Poor data availability on soil hydraulic properties in tropical regions hampers many studies, including crop and environmental modeling. The high cost and effort of measurement and the increasing demand for such data have driven researchers to search for... ver más
Revista: Water

 
Liqiu Chen, Chongshi Gu, Sen Zheng and Yanbo Wang    
Real and effective monitoring data are crucial in assessing the structural safety of dams. Gross errors, resulting from manual mismeasurement, instrument failure, or other factors, can significantly impact the evaluation process. It is imperative to elim... ver más
Revista: Water

 
Yongqi Liu, Guibing Hou, Baohua Wang, Yang Xu, Rui Tian, Tao Wang and Hui Qin    
Flood control operation of cascade reservoirs is an important technology to reduce flood disasters and increase economic benefits. Flood forecast information can help reservoir managers make better use of flood resources and reduce flood risks. In this p... ver más
Revista: Water

 
Yong Liu, Xiaohui Yan, Wenying Du, Tianqi Zhang, Xiaopeng Bai and Ruichuan Nan    
The current work proposes a novel super-resolution convolutional transposed network (SRCTN) deep learning architecture for downscaling daily climatic variables. The algorithm was established based on a super-resolution convolutional neural network with t... ver más
Revista: Water

 
Min Li, Zhirui Cui and Tianyu Fan    
In order to further improve the accuracy of flood routing, this article uses the Variable Exponential Nonlinear Muskingum Model (VEP-NMM), combined with the Artificial Rabbit Optimization (ARO) algorithm for parameter calibration, to construct the ARO-VE... ver más
Revista: Water