loading
Documents

Research.Publish.Connect.

Paper

Authors: Maysa I. A. Almulla Khalaf 1 and John Q. Gan 2

Affiliations: 1 School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, CO4 3SQ, Colchester, Essex, U.K., Department of Computer Science, Baghdad University, Baghdad and Iraq ; 2 School of Computer Science and Electronic Engineering, University of Essex, Wivenhoe Park, CO4 3SQ, Colchester, Essex and U.K.

ISBN: 978-989-758-327-8

Keyword(s): Stacked Autoencoder, Deep Learning, Feature Learning, Effective Weight Initialisation.

Abstract: This paper investigates deep classifier structures with stacked autoencoder (SAE) for higher-level feature extraction, aiming to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space, such as overfitting and vanishing/exploding gradients. A three-stage learning algorithm is proposed in this paper for training deep multilayer perceptron (DMLP) as the classifier. At the first stage, unsupervised learning is adopted using SAE to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Cross-validation is adopted to determine the network structures and the values of the learning parameters, and test datasets unseen in the cross-validation are use d to evaluate the performance of the DMLP trained using the three-stage learning algorithm, in comparison with support vector machines (SVM) combined with SAE. Experimental results have demonstrated the advantages and effectiveness of the proposed method. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.91.41.87

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Khalaf, M. and Gan, J. (2018). Deep Classifier Structures with Autoencoder for Higher-level Feature Extraction.In Proceedings of the 10th International Joint Conference on Computational Intelligence - Volume 1: IJCCI, ISBN 978-989-758-327-8, pages 31-38. DOI: 10.5220/0006883000310038

@conference{ijcci18,
author={Maysa I. A. Almulla Khalaf. and John Q. Gan.},
title={Deep Classifier Structures with Autoencoder for Higher-level Feature Extraction},
booktitle={Proceedings of the 10th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,},
year={2018},
pages={31-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006883000310038},
isbn={978-989-758-327-8},
}

TY - CONF

JO - Proceedings of the 10th International Joint Conference on Computational Intelligence - Volume 1: IJCCI,
TI - Deep Classifier Structures with Autoencoder for Higher-level Feature Extraction
SN - 978-989-758-327-8
AU - Khalaf, M.
AU - Gan, J.
PY - 2018
SP - 31
EP - 38
DO - 10.5220/0006883000310038

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.