• Home
  • Search
  • A Hardware-Oriented Dropout Algorithm for Efficient FPGA Implementation
  • Cite Icon5
  • https://doi.org/10.1007/978-3-319-70136-3_87Copy DOI Icon

A Hardware-Oriented Dropout Algorithm for Efficient FPGA Implementation

  • Jan 1, 2017
  • Yoeng Jye Yeoh +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper proposes a hardware oriented dropout algorithm for an efficient field-programmable gate array (FPGA) implementation. Dropout is a regularization technique, which is commonly used in neural networks such as multilayer perceptrons (MLPs), convolutional neural networks (CNNs), among others. To generate a dropout mask to randomly drop neurons during training phase, random number generators (RNGs) are usually used in software implementations. However, RNGs consume considerable FPGA resources in hardware implementations. The proposed method is able to minimize the resources required for FPGA implementation of dropout by performing a simple rotation operation to a predefined dropout mask. We apply the proposed method to MLPs and CNNs and evaluate them on MNIST and CIFAR-10 classification. In addition, we employ the proposed method in GoogLeNet training using own dataset to develop a vision system for home service robots. The experimental results demonstrate that the proposed method achieves the same regularized effect as the ordinary dropout algorithm. Logic synthesis results show that the proposed method significantly reduces the consumption of FPGA resources in comparison to the ordinary RNG-based approaches.

Similar Papers
  • Research Article

"Enhanced DA Algorithm for FIR Filter Design and FPGA Implementation"

  • May 31, 2024
  • International Journal for Research in Applied Science and Engineering Technology
  • Akshya Dwivedi
  • Conference Article

Field Programmable Gate Array implementation of Conic Section Function Neural Network: An alternative to analog CSFNN circuitry

  • Jun 01, 2012
  • Metin Elitas +2
  • Research Article
  • Citations10

Towards Lattice Quantum Chromodynamics on FPGA devices

  • Nov 11, 2019
  • Computer Physics Communications
  • Grzegorz Korcyl +1
  • Research Article
  • Citations10

Fringe pattern demodulation using the one-dimensional continuous wavelet transform: field-programmable gate array implementation

  • Feb 28, 2013
  • Applied Optics
  • Abdulbasit Abid
  • Research Article
  • Citations15

BOTDA Fiber Sensor System Based on FPGA Accelerated Support Vector Regression

  • Oct 18, 2019
  • IEEE Transactions on Instrumentation and Measurement
  • Huan Wu +4
  • Research Article

A Design of Network Reconfigurable Universal CNN Accelerator Based on FPGA

  • Jan 23, 2026
  • ACM Transactions on Embedded Computing Systems
  • Wenhua Ye +4
  • Research Article
  • Citations58

Hardware Design of Real Time Epileptic Seizure Detection Based on STFT and SVM

  • Jan 01, 2018
  • IEEE Access
  • Hongda Wang +2
  • Conference Article
  • Citations4

A Random Number Generator Based on Irregular Sampling and Transient Effect Ring Oscillators

  • Sep 30, 2020
  • Burak Acar +1
  • Book Chapter
  • Citations12

FPGA Implementation of Feature Extraction and Neural Network Classifier for Handwritten Digit Recognition

  • Jan 01, 2004
  • Dongsheng Shen +2
  • Research Article
  • Citations7

FPGA implementation of a high‐speed, real‐time, windowed standard deviation filter

  • Jan 01, 2016
  • Electronics Letters
  • J Herbert +3
  • Conference Article
  • Citations40

An FPGA implementation of parallel ICA for dimensionality reduction in hyperspectral images

  • Dec 27, 2004
  • Hongtao Du +1
  • Conference Article
  • Citations43

Runtime assignment of reconfigurable hardware components for image processing pipelines

  • Apr 09, 2003
  • H Quinn +3
  • Research Article
  • Citations207

Feedforward Neural Network Implementation in FPGA Using Layer Multiplexing for Effective Resource Utilization

  • May 01, 2007
  • IEEE Transactions on Neural Networks
  • S Himavathi +2
  • Research Article
  • Citations20

Bit‐parallel systolic multiplier over for irreducible trinomials with ASIC and FPGA implementations

  • Mar 28, 2018
  • IET Circuits, Devices & Systems
  • Sudha Ellison Mathe +1
  • Research Article
  • Citations24

High-speed FPGA implementation of orthogonal matching pursuit for compressive sensing signal reconstruction

  • Aug 03, 2018
  • Computers & Electrical Engineering
  • Önder Polat +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.