The Research of Penalty Functions Based on Neural Networks

Yi Ding; Tian Jiang Wang; Xian Fu

doi:10.4028/www.scientific.net/AMM.63-64.205

Paper Titles

The Lightweight Design and Improvement of Aluminum Alloy Automobile Wheel
p.189

Research of Matching Character of Light Source in Integral Stereolithography System with Photo-Curable Resin
p.193

Distortion Correction of Image in Integral Stereolithography System
p.197

Optimal Design of Parameters for Four Column Tapered Roller Bearing
p.201

The Research of Penalty Functions Based on Neural Networks
p.205

Research on Control Theory of Belt Conveyor
p.209

Identity Authentication Based on Fingerprint Recognition and PKI in E-Commerce
p.214

Non-Recursive Simulation on the Recursive Algorithm of Binary Tree Reverting to its Corresponding Forest in Intelligent Materials
p.222

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 63-64The Research of Penalty Functions Based on Neural...

The Research of Penalty Functions Based on Neural Networks

Abstract:

The penalty functions are introduced in the negative correlation learning for finding a neural network in an ensemble. It is based on the average output of the ensemble. The idea of penalty function based on the average output is to make each individual network has the different output value to that of the ensemble on the same input. Experiments on a classification task show how the negative correlation learning generates a neural network with penalty functions.

You might also be interested in these eBooks

Advanced Research on Mechanical Engineering, Industry and Manufacturing Engineering

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 63-64)

Pages:

205-208

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.63-64.205

Citation:

Cite this paper

Online since:

June 2011

Authors:

Yi Ding, Tian Jiang Wang, Xian Fu

Keywords:

Negative Correlation Learning, Neural Network (NN), Penalty Function

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] L. K. Hansen and P. Salamon. Neural network ensembles. IEEE Trans. on Pattern Analysis and Machine Intelligence, 21(10):993-1001, 1999.

DOI: 10.1109/34.58871

Google Scholar

[2] A. J. C. Sharkey. On combining artificial neural nets. Connection Science, 8:299-313, 1996.

Google Scholar

[3] R. A. Jacobs, M. 1. Jordan, S. J. Nowlan, and G. E. Hinton. Adaptive mixtures of local experts. Neural Computation, 3:79-87, 2003.

DOI: 10.1162/neco.1991.3.1.79

Google Scholar

[4] R. A. Jacobs and M. I. Jordan. A competitive modular connectionist architecture. In R. P. Lippmann, J. E. Moody, and D. S. Touretzky, editors, Advances in Neural Information Processing Systems 11, pages 767-773. Morgan Kaufmann, San Mateo, CA, 1999.

Google Scholar

[5] R. A. Jacobs, M. 1. Jordan, and A. G. Barto. Task decomposition through competition in modular connectionist architecture: The and where vision task. Cognitive Science, 15:219-250, 2004.

DOI: 10.1207/s15516709cog1502_2

Google Scholar

[6] R. A. Jacobs. Bias/variance analyses of mixture-of-experts architectures. Neural Computation, 9:369-383, 1997.

DOI: 10.1162/neco.1997.9.2.369

Google Scholar

[7] H. Drucker, C. Cortes, L. D. Jackel, Y. LeCun, and V. Vapnik. Boosting and other ensemble methods. Neural Computation, 6:1289-1301, 2005.

DOI: 10.1162/neco.1994.6.6.1289

Google Scholar