• Home
  • Search
  • An Ordered Aggregation-Based Ensemble Selection Method of Lightweight Deep Neural Networks With Random Initialization
  • https://doi.org/10.1109/access.2022.3220666Copy DOI Icon

An Ordered Aggregation-Based Ensemble Selection Method of Lightweight Deep Neural Networks With Random Initialization

Show More
  • Abstract
  • Highlights & Summary
  • Literature Map
  • References
  • Similar Papers
Abstract

Due to the popularity of 5G connectivity and The Internet of Things sensors, deep learning algorithms are being extended to edge devices. Compared with AI(Artificial Intelligence) cloud platforms, the deployment of deep neural networks on edge devices must focus on low power consumption, low latency, stability and reliability. In recent years, the development of lightweight deep neural network architecture has provided a basis for the deployment of deep neural networks on edge devices. However, the shortcomings of deep neural networks, such as overconfidence, vulnerability to adversarial attack, and easy over fitting when samples are insufficient, still limit their applications in many fields. One of the ways to compensate for these defects is to use deep ensemble. An ordered aggregation-based ensemble selection algorithm is proposed, which uses soft-margin as the importance assessment metric to take full advantage of the diversity and complementarity of lightweight deep neural networks obtained from different initialization training, so as to improve the overall performance of multiple edge devices. The experimental results show that this algorithm has a significant improvement in generalization performance compared with random ensemble and ordered aggregation algorithms based on accuracy or diversity, and provides a new complementary idea for the deployment of lightweight deep neural networks on edge devices.

Similar Papers
  • Research Article
  • Citations134

DORY: Automatic End-to-End Deployment of Real-World DNNs on Low-Cost IoT MCUs

  • Aug 01, 2021
  • IEEE Transactions on Computers
  • Alessio Burrello +5
  • Conference Article
  • Citations1

An Automated Approach to Accelerate DNNs on Edge Devices

  • May 01, 2021
  • Ujjawal Chugh +6
  • Dissertation

Deep learning acceleration on edge devices with algorithm/hardware co-design

  • Jan 01, 2022
  • Mengshu Sun
  • PDF
  • Research Article
  • Citations2

Conflict-Resilient Incremental Offloading of Deep Neural Networks to the Edge of Smart Environment

  • Jun 07, 2021
  • Mathematical Problems in Engineering
  • Zhongmin Chen +5
  • Conference Article
  • Citations4

Work in Progress: Mobile or FPGA? A Comprehensive Evaluation on Energy Efficiency and a Unified Optimization Framework

  • May 01, 2021
  • Geng Yuan +11
  • Research Article
  • Citations4

Mobile or FPGA? A Comprehensive Evaluation on Energy Efficiency and a Unified Optimization Framework

  • Sep 30, 2022
  • ACM Transactions on Embedded Computing Systems
  • Geng Yuan +12
  • Conference Article
  • Citations113

Characterizing the Deployment of Deep Neural Networks on Commercial Edge Devices

  • Nov 01, 2019
  • Ramyad Hadidi +5
  • Conference Article
  • Citations4

Enhancing the Security of Collaborative Deep Neural Networks: An Examination of the Effect of Low Pass Filters

  • Jun 05, 2023
  • Adewale A Adeyemo +1
  • Conference Article
  • Citations21

SECDA: Efficient Hardware/Software Co-Design of FPGA-based DNN Accelerators for Edge Inference

  • Oct 01, 2021
  • Jude Haris +4
  • Conference Article

Energy-Efficient DNNs on FPGAs for Edge-Cloud Computer Vision

  • Sep 01, 2025
  • Qaisar Farooq +1
  • Conference Article
  • Citations6

Post-Training Quantization for Energy Efficient Realization of Deep Neural Networks

  • Dec 01, 2022
  • Cecilia Latotzke +2
  • PDF
  • Research Article
  • Citations191

Quantization and Deployment of Deep Neural Networks on Microcontrollers

  • Apr 23, 2021
  • Sensors (Basel, Switzerland)
  • Pierre-Emmanuel Novac +4
  • PDF
  • Research Article
  • Citations54

Lightweight Shufflenet Based CNN for Arrhythmia Classification

  • Jan 01, 2022
  • IEEE Access
  • Huruy Tesfai +6
  • Conference Article
  • Citations3

Investigating Mobile Edge-Cloud Trade-Offs of Object Detection with YOLO

  • Oct 07, 2019
  • W F MagalhãEs +4
  • Research Article
  • Citations26

BitSystolic: A 26.7 TOPS/W 2b~8b NPU With Configurable Data Flows for Edge Devices

  • Dec 21, 2020
  • IEEE Transactions on Circuits and Systems I: Regular Papers
  • Qing Yang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.