• Home
  • Search
  • Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices
  • Open Access IconOpen Access
  • Cite Icon14
  • https://doi.org/10.1145/3225209.3225214Copy DOI Icon

Resource and data optimization for hardware implementation of deep neural networks targeting FPGA-based edge devices

  • Jun 23, 2018
  • Xinheng Liu +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Recently, as machine learning algorithms have become more practical, there has been much effort to implement them on edge devices that can be used in our daily lives. However, unlike server-scale devices, edge devices are relatively small and thus have much more limited resources. Therefore, control of resource usage and hardware optimization play an important role when we implement machine learning algorithms on an edge device. In this paper, we target convolutional neural networks (CNN) and explore various optimization and design techniques to realize them on FPGA devices. The key idea explored in this paper is Backward Pipeline Scheduling together with Latency Balancing which optimize the pipeline between CNN layers in order to significantly reduce the overall latency for processing a single image. We also develop a batch processing design to improve the throughput of the FPGA solution. We have achieved latency of 175.7µs for classifying one image in the MNIST data set using LeNet and 653.4µs for classifying one image in Cifar-10 data set using CifarNet. Without retraining, we are still able to maintain high accuracy of 97.6% for MNIST data set and 83.6% for the Cifar-10 data set. Our achieved single- image latency is 5.2x faster for LeNet and 1.95x faster for CifarNet compared to the NVIDIA Jetson TX1 solution.

Similar Papers
  • PDF
  • Research Article
  • Citations25

Research on improved convolutional wavelet neural network

  • Sep 09, 2021
  • Scientific Reports
  • Jingwei Liu +4
  • Preprint Article
  • Citations20

Optimization of Convolutional Neural Network Using the Linearly Decreasing Weight Particle Swarm Optimization

  • Jan 16, 2020
  • Proceedings of the Annual Conference of JSAI
  • T Serizawa +1
  • Conference Article
  • Citations5

Quantized Guided Pruning for Efficient Hardware Implementations of Deep Neural Networks

  • Jun 01, 2020
  • Ghouthi Boukli Hacene +4
  • PDF
  • Research Article
  • Citations3

Logarithm Decreasing Inertia Weight Particle Swarm Optimization Algorithms for Convolutional Neural Network

  • May 27, 2022
  • JUITA: Jurnal Informatika
  • Murinto Murinto +1
  • Research Article
  • Citations108

An Architecture to Accelerate Convolution in Deep Neural Networks

  • Apr 01, 2018
  • IEEE Transactions on Circuits and Systems I: Regular Papers
  • Arash Ardakani +3
  • Research Article
  • Citations2

Metasurface-Generated Large and Arbitrary Analog Convolution Kernels for Accelerated Machine Vision

  • Dec 04, 2024
  • ACS Photonics
  • Ruiqi Liang +6
  • Research Article
  • Citations47

Generative adversarial network based synthetic data training model for lightweight convolutional neural networks

  • May 20, 2023
  • Multimedia Tools and Applications
  • Ishfaq Hussain Rather +1
  • Research Article
  • Citations15

Lightening the Load with Highly Accurate Storage- and Energy-Efficient LightNNs

  • Sep 30, 2018
  • ACM Transactions on Reconfigurable Technology and Systems
  • Ruizhou Ding +3
  • Conference Article
  • Citations8

Spiking Approximations of the MaxPooling Operation in Deep SNNs

  • Jul 18, 2022
  • Ramashish Gaurav +2
  • Research Article
  • Citations81

CerCan·Net: Cervical cancer classification model via multi-layer feature ensembles of lightweight CNNs and transfer learning

  • Nov 01, 2023
  • Expert Systems with Applications
  • Omneya Attallah
  • Research Article
  • Citations4

Uncertainty handling in convolutional neural networks

  • Jan 01, 2022
  • Neural Computing & Applications
  • Elyas Rashno +2
  • Research Article
  • Citations9

High-Speed Multi-Layer Convolutional Neural Network Based on Free-Space Optics

  • Aug 01, 2022
  • IEEE Photonics Journal
  • Hoda Sadeghzadeh +1
  • Research Article
  • Citations3

Convolutional networks with short-term memory effects

  • Feb 01, 2023
  • Microprocessors and Microsystems
  • Chencheng Gong +2
  • PDF
  • Research Article

Analysis of the Layers in Convolutional Neural Network in the Context of Text Recognition

  • Aug 01, 2018
  • Indian Journal of Science and Technology
  • Vladimir Pe�A Mauricio +4
  • Research Article
  • Citations124

CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference

  • Jun 01, 2021
  • IEEE Journal of Solid-State Circuits
  • Zhiyu Chen +8
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.