[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.1145/3366650.3366651acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccbdConference Proceedingsconference-collections
research-article

Enhancing Feed-Forward Neural Network in Image Classification

Published: 18 October 2019 Publication History

Abstract

In this paper. the researcher use Feed Forward Neural Network for image classification. The objective of this paper is to Enhancing the structure of FFNN by adding dropout method into the input layer and hidden layer to prevent over-fitting the network and then initialized by random uniform initializer for each layer then setting a bias of zeros, also adding the following activation function ReLu&Softmax to the network and the dataset that the researcher use was the MNIST-handwritten numbers. The dropout method is one of the easy and efficient regularization methods that avoids overfitting which stochastically drops out some neurons and trains the network at each weight update. After that, researcher determines the performance of the result by evaluating the FFNN with dropout on the basis of loss and accuracy to take the average of the difference between the standard FFNN and CNN. The result of FFNN with dropout method had an average of 99.86% accuracy and 0.47% of loss, the standard FFNN got 98.13% accuracy and loss of 9.15%, while the CNN had an average of 99.26% accuracy and 2.39% of loss. As the training process of neural network is an iterative process comprising forward propagation, speed improvement using dropout would also provide a significantly decreased training time.

References

[1]
D. S. S. S. Enakshi Jana, 2018. Research on Skin Cancer Cell Detection using Image Processing. 2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) pp. 1--8 DOI=https://doi.org/10.1109/ICCIC.2017.8524554.
[2]
H. G. 2018. Heather Hunter. Comparison of Feed Forward Neural Networks and Convolutional Neural Networks for SAR Automatic Target Recognition. pp. 1022--1027.
[3]
M. A. S. A. S. Y. M. M. 2017. Ching Loong Seow. Improved Architecture of the Feedforward Neural Network for Image Recognition. IEACon 2016-2016 IEEE Industrial Electronics and Applications Conference. pp. 280--286. DOI=https://doi.org/10.1109/IEACON.2016.8067392
[4]
M. K. M. V. A. B. 2016. Likewin Thomas. Discovery of Optimal Neurons and Hidden Layers in Feed-Forward Neural Network. 2016 IEEE International Conference on Emerging Technologies and Innovative Business Practices for the Transformation of Societies, EmergiTech 2016. pp. 286--291, 2016. DOI=https://doi.org/10.1109/EmergiTech.2016.7737353
[5]
A. T. c. P. a. V. k. N. 2016. Shubhangi Khobragade. Automatic Deteetion of Major Lung Diseases Using Chest Radiographs and Classifieation by Feed-forward Artificial Neural Network. 1st IEEE International Conference on Power Electronics. Intelligent Control and Energy Systems (ICPEICES-2016). pp. 1--5.
[6]
L. G. Y.-X. W. L.-P. M. J. M. F. M. 2018. Liang-Yan Gui. Factorized Convolutional Networks: Unsupervised Fine-Tuning for Image Clustering. 2018 IEEE Winter Conference on Applications of Computer Vision pp. 1205--1214. DOI=https://doi.org/10.1109/WACV.2018.00137
[7]
E. P. F. A. N. L. A. P. J. L. A. a. B. C. Gi Hyun Lim. 2017. Neural regularization jointly involving neurons and connections for robust image classification. 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2017). pp. 336--341.
[8]
L. T. X. L. J. J. J. H. Shengyu Pei. 2017. Feed-Forward Network for Cancer Detection. 2017--13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). pp. 697--701.
[9]
P. M. Baggenstoss. 2018. On the Duality Between Belief Networks and Feed-Forward Neural Networks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS. pp. 1--11.
[10]
X. G. Haibing Wu. 2015. Towards dropout training for convolutional neural networks. vol. 71, pp. 1--10, 2015. DOI=http://dx.doi.org/10.1016/j.neunet.2015.07.007
[11]
H.-G. K. H.-J. C. ByungSoo Ko. 2017. Controlled Dropout: a Different Dropout for Improving Training Speed on Deep Neural Network. 2017 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2017. Vols. 2017-Janua, pp. 972--977, 2017. DOI=https://doi.org/10.1109/SMC.2017.8122736
[12]
L. P. P. K. Samuel Rota Bulò. 2016. Dropout distillation. Proceedings of the 33rd International Conference on Machine Learning, New York, NY, USA, 2016. Volume 48. pp. 99--107, 2016. DOI=
[13]
H. N. Sota Sawaguchi. 2018. Slightly-slacked dropout for improving neural network learning on FPGA. 2018 The Korean Institute of Communications and Information Sciences (KICS). vol. 4, no. 2, pp. 75--80. DOI=https://doi.org/10.1016/j.icte.2018.04.006
[14]
G. H. A. K. I. S. R. S. Nitish Srivastava. 2014. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. pp. 1929--1958.
[15]
P. S. Pierre Baldi, 2014. "The dropout learning algorithm," vol. 210, no. 1, pp. 78--122. DOI= http://dx.doi.org/10.1016/j.artint.2014.02.004

Cited By

View all
  • (2023)An Improved Music genre classification using Convolutional Neural Network and Spectrograms2023 International Conference on System, Computation, Automation and Networking (ICSCAN)10.1109/ICSCAN58655.2023.10395616(1-6)Online publication date: 17-Nov-2023

Index Terms

  1. Enhancing Feed-Forward Neural Network in Image Classification

    Recommendations

    Comments

    Please enable JavaScript to view thecomments powered by Disqus.

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICCBD '19: Proceedings of the 2nd International Conference on Computing and Big Data
    October 2019
    173 pages
    ISBN:9781450372909
    DOI:10.1145/3366650
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 18 October 2019

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. CNN
    2. Dropout
    3. Feed-Forward

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICCBD 2019

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)15
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 21 Dec 2024

    Other Metrics

    Citations

    Cited By

    View all
    • (2023)An Improved Music genre classification using Convolutional Neural Network and Spectrograms2023 International Conference on System, Computation, Automation and Networking (ICSCAN)10.1109/ICSCAN58655.2023.10395616(1-6)Online publication date: 17-Nov-2023

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media