Next Article in Journal
About Linda Again: How Narratives and Group Reasoning Can Influence Conjunction Fallacy
Previous Article in Journal
Joint Optimization of Pico-Base-Station Density and Transmit Power for an Energy-Efficient Heterogeneous Cellular Network
Previous Article in Special Issue
An Improved Approach for Text Sentiment Classification Based on a Deep Neural Network via a Sentiment Attention Mechanism
Open AccessArticle

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

Institute of Computing, University of Campinas, Campinas 13083-852, SP, Brazil
*
Authors to whom correspondence should be addressed.
Future Internet 2019, 11(10), 209; https://doi.org/10.3390/fi11100209
Received: 3 September 2019 / Revised: 26 September 2019 / Accepted: 26 September 2019 / Published: 29 September 2019
(This article belongs to the Special Issue Innovative Topologies and Algorithms for Neural Networks)
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. View Full-Text
Keywords: Internet of Things; convolutional neural networks; graph partitioning; distributed systems; resource-efficient inference Internet of Things; convolutional neural networks; graph partitioning; distributed systems; resource-efficient inference
Show Figures

Figure 1

MDPI and ACS Style

Martins Campos de Oliveira, F.; Borin, E. Partitioning Convolutional Neural Networks to Maximize the Inference Rate on Constrained IoT Devices. Future Internet 2019, 11, 209.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop