skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Evolving Energy Efficient Convolutional Neural Networks

Abstract

As deep neural networks have been deployed in more and more applications over the past half decade and are finding their way into an ever increasing number of operational systems, their energy consumption becomes a concern whether running in the datacenter or on edge devices. Hyperparameter optimization and automated network design for deep learning is a quickly growing field, but much of the focus has remained only on optimizing for the performance of the machine learning task. In this work, we demonstrate that the best performing networks created through this automated network design process have radically different computational characteristics (e.g. energy usage, model size, inference time), presenting the opportunity to utilize this optimization process to make deep learning networks more energy efficient and deployable to smaller devices. Optimizing for these computational characteristics is critical as the number of applications of deep learning continues to expand.

Authors:
ORCiD logo [1]; ORCiD logo [1];  [1]; ORCiD logo [1];  [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
OSTI Identifier:
1606807
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: 2nd Workshop on Energy-Efficient Machine Learning and Big Data Analytics (in conjuction with IEEE Big Data) - Los Angeles, California, United States of America - 11/9/2019 5:00:00 AM-11/12/2019 5:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Young, Steven, Devineni, Pravallika, Parsa, Maryam, Johnston, Travis, Kay, Bill, Patton, Robert, Schuman, Catherine, Rose, Derek, and Potok, Thomas. Evolving Energy Efficient Convolutional Neural Networks. United States: N. p., 2019. Web. doi:10.1109/BigData47090.2019.9006239.
Young, Steven, Devineni, Pravallika, Parsa, Maryam, Johnston, Travis, Kay, Bill, Patton, Robert, Schuman, Catherine, Rose, Derek, & Potok, Thomas. Evolving Energy Efficient Convolutional Neural Networks. United States. https://doi.org/10.1109/BigData47090.2019.9006239
Young, Steven, Devineni, Pravallika, Parsa, Maryam, Johnston, Travis, Kay, Bill, Patton, Robert, Schuman, Catherine, Rose, Derek, and Potok, Thomas. 2019. "Evolving Energy Efficient Convolutional Neural Networks". United States. https://doi.org/10.1109/BigData47090.2019.9006239. https://www.osti.gov/servlets/purl/1606807.
@article{osti_1606807,
title = {Evolving Energy Efficient Convolutional Neural Networks},
author = {Young, Steven and Devineni, Pravallika and Parsa, Maryam and Johnston, Travis and Kay, Bill and Patton, Robert and Schuman, Catherine and Rose, Derek and Potok, Thomas},
abstractNote = {As deep neural networks have been deployed in more and more applications over the past half decade and are finding their way into an ever increasing number of operational systems, their energy consumption becomes a concern whether running in the datacenter or on edge devices. Hyperparameter optimization and automated network design for deep learning is a quickly growing field, but much of the focus has remained only on optimizing for the performance of the machine learning task. In this work, we demonstrate that the best performing networks created through this automated network design process have radically different computational characteristics (e.g. energy usage, model size, inference time), presenting the opportunity to utilize this optimization process to make deep learning networks more energy efficient and deployable to smaller devices. Optimizing for these computational characteristics is critical as the number of applications of deep learning continues to expand.},
doi = {10.1109/BigData47090.2019.9006239},
url = {https://www.osti.gov/biblio/1606807}, journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {12}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: