A Novel Deep Learning Approach: Stacked Evolutionary Auto-encoder

Cai, Y; Cai, Z; Zeng, M; Liu, X; Wu, J; Wang, G

A Novel Deep Learning Approach: Stacked Evolutionary Auto-encoder

Cai, Y Cai, Z Zeng, M Liu, X Wu, J Wang, G

Permalink

Publication Type:: Conference Proceeding
Citation:: Proceedings of the International Joint Conference on Neural Networks, 2018, 2018-July
Issue Date:: 2018-10-10

Closed Access

	Filename	Description	Size
	08489138.pdf	Published version	2.13 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Cai, Y	en_US
dc.contributor.author	Cai, Z	en_US
dc.contributor.author	Zeng, M	en_US
dc.contributor.author	Liu, X	en_US
dc.contributor.author	Wu, J	en_US
dc.contributor.author	Wang, G	en_US
dc.date.issued	2018-10-10	en_US
dc.identifier.citation	Proceedings of the International Joint Conference on Neural Networks, 2018, 2018-July	en_US
dc.identifier.isbn	9781509060146	en_US
dc.identifier.uri	http://hdl.handle.net/10453/132971
dc.description.abstract	© 2018 IEEE. Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification prob- lems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.	en_US
dc.relation.ispartof	Proceedings of the International Joint Conference on Neural Networks	en_US
dc.relation.isbasedon	10.1109/IJCNN.2018.8489138	en_US
dc.title	A Novel Deep Learning Approach: Stacked Evolutionary Auto-encoder	en_US
dc.type	Conference Proceeding
utslib.citation.volume	2018-July	en_US
utslib.for	0805 Distributed Computing	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US
pubs.volume	2018-July	en_US

Abstract:

© 2018 IEEE. Deep neural networks have been successfully applied to many data mining problems in recent works. The training of deep neural networks relies heavily upon gradient descent methods, however, which may lead to the failure of training due to the vanishing gradient (or exploding gradient) and local optima problems. In this paper, we present SEvoAE method based on using Evolutionary Multiobjective optimization (EMO) algorithm to train single layer auto-encoder, and sequentially learning deeper representation in a stacking way. SEvoAE is able to achieve accurate feature representation with good sparseness by globally simultaneously optimizing two conflicting objective functions and allows users to flexibly design objective functions and evolutionary optimizers. We compare results of the proposed method with existing architectures for seven classification prob- lems, showing that the proposed method is able to outperform existing methods with a reduced risk of overfitting the training data.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/132971