2018/06/12 by Haichuan Yang, Yuhao Zhu, Yang, Haichuan +3 · 1 voice · 2 citations
Computer Science · Engineering · Mathematics · #Advanced Neural Network Applications #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Video Surveillance and Tracking Methods #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1806.04321
openalex publication_date 2018/06/12 · arxiv published 2018/06/12 · openalex created_date 2019/02/21 · arxiv updated 2019/06/02 · openalex updated_date 2026/07/28
Deep Neural Networks (DNNs) are increasingly deployed in highly energy-constrained environments such as autonomous drones and wearable devices while at the same time must operate in real-time. Therefore, reducing the energy consumption has become a major design consideration in DNN training. This paper proposes the first end-to-end DNN training framework that provides quantitative energy consumption guarantees via weighted sparse projection and input masking. The key idea is to formulate the DNN training as an optimization problem in which the energy budget imposes a previously unconsidered optimization constraint. We integrate the quantitative DNN energy estimation into the DNN training process to assist the constrained optimization. We prove that an approximate algorithm can be used to efficiently solve the optimization problem. Compared to the best prior energy-saving methods, our framework trains DNNs that provide higher accuracies under same or lower energy budgets. Code is publicly available.