Layered-CasPer: Layered cascade artificial neural networks

Tengfei Shen; Dingyun Zhu

doi:10.1109/IJCNN.2012.6252799

Layered-CasPer: Layered cascade artificial neural networks

Tengfei Shen^*, Dingyun Zhu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

Abstract

Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A-CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A-CasPer algorithm in terms of the network architecture - the Layered-CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered-CasPer are the same as A-CasPer. The Layered-CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A-CasPer, and AT-CasPer. It is shown that Layered-CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered-CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.

Original language	English
Title of host publication	2012 International Joint Conference on Neural Networks, IJCNN 2012
DOIs	https://doi.org/10.1109/IJCNN.2012.6252799
Publication status	Published - 2012
Event	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 - Brisbane, QLD, Australia Duration: 10 Jun 2012 → 15 Jun 2012

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks

Conference

Conference	2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
Country/Territory	Australia
City	Brisbane, QLD
Period	10/06/12 → 15/06/12

Access to Document

10.1109/IJCNN.2012.6252799

Cite this

@inproceedings{6da8a92817ae4f719d6836e369170203,

title = "Layered-CasPer: Layered cascade artificial neural networks",

abstract = "Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A-CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A-CasPer algorithm in terms of the network architecture - the Layered-CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered-CasPer are the same as A-CasPer. The Layered-CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A-CasPer, and AT-CasPer. It is shown that Layered-CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered-CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.",

keywords = "A-CasPer, AT-CasPer, CasCor, CasPer, Cascade, Layered-CasPer, constructive algorithms, feedforward neural network",

author = "Tengfei Shen and Dingyun Zhu",

year = "2012",

doi = "10.1109/IJCNN.2012.6252799",

language = "English",

isbn = "9781467314909",

series = "Proceedings of the International Joint Conference on Neural Networks",

booktitle = "2012 International Joint Conference on Neural Networks, IJCNN 2012",

note = "2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012 ; Conference date: 10-06-2012 Through 15-06-2012",

}

Shen, T & Zhu, D 2012, Layered-CasPer: Layered cascade artificial neural networks. in 2012 International Joint Conference on Neural Networks, IJCNN 2012., 6252799, Proceedings of the International Joint Conference on Neural Networks, 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012, Brisbane, QLD, Australia, 10/06/12. https://doi.org/10.1109/IJCNN.2012.6252799

TY - GEN

T1 - Layered-CasPer

T2 - 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012

AU - Shen, Tengfei

AU - Zhu, Dingyun

PY - 2012

Y1 - 2012

N2 - Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A-CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A-CasPer algorithm in terms of the network architecture - the Layered-CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered-CasPer are the same as A-CasPer. The Layered-CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A-CasPer, and AT-CasPer. It is shown that Layered-CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered-CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.

AB - Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A-CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A-CasPer algorithm in terms of the network architecture - the Layered-CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered-CasPer are the same as A-CasPer. The Layered-CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A-CasPer, and AT-CasPer. It is shown that Layered-CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered-CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.

KW - A-CasPer

KW - AT-CasPer

KW - CasCor

KW - CasPer

KW - Cascade

KW - Layered-CasPer

KW - constructive algorithms

KW - feedforward neural network

UR - http://www.scopus.com/inward/record.url?scp=84865063699&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2012.6252799

DO - 10.1109/IJCNN.2012.6252799

M3 - Conference contribution

SN - 9781467314909

T3 - Proceedings of the International Joint Conference on Neural Networks

BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012

Y2 - 10 June 2012 through 15 June 2012

ER -

Layered-CasPer: Layered cascade artificial neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this