Can I read Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms on EtoBox?

Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms by Ko, Jong Hwan; Na, Taesik; Amir, Mohammad Faisal; Mukhopadhyay, Saibal is a scholarly article available to read on EtoBox.

What is Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms about?

This paper introduces partitioning an inference task of a deep neural network between an edge and a host platform in the IoT environment. We present a DNN as an encoding pipeline, and propose to transmit the output feature space of an intermediate layer to the host. The lossless or lossy encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform. Simulation results show that partitioning a DNN at the end of convolutional (feature extraction) layers coupled with feature space encoding enables significant improvement in the energy-efficiency and throughput over the baseline configurations that perform the entire inference at the edge or at the host.

Author

Ko, Jong Hwan; Na, Taesik; Amir, Mohammad Faisal; Mukhopadhyay, Saibal

Published

2018

Language

EN