Output partitioning of neural networks

Neurocomputing

Volumn 68, Issue 1-4, 2005, Pages 38-53

  Guan, Shen Uei ^a   Yinan, Qi ^a   Tan, Syn Kiat ^a   Li, Shanchun ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Constructive learning algorithm; Neural networks; Output partitioning

Indexed keywords

BACKPROPAGATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; PATTERN RECOGNITION;

CONSTRUCTIVE LEARNING ALGORITHM; INCREMENTAL PARTITIONING; OUTPUT PARTITIONING;

NEURAL NETWORKS;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATION; CLASSIFICATION; CONTROLLED STUDY; DATA ANALYSIS; INFORMATION PROCESSING; LEARNING; MATHEMATICAL COMPUTING; PRIORITY JOURNAL; TASK PERFORMANCE; TRAINING; VALIDATION PROCESS;

EID: 24144491262     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2005.02.002     Document Type: Article

References (31)

1. T. Ash Dynamic node creation in backpropagation networks Connect. Sci. 1 4 1989 365-375
2. G. Auda M. Kamel H. Raafat Modular neural network architectures for classification IEEE International Conference on Neural Networks V2 1996 1279-1284
3. E.B. Baum D. Haussler What size net gives valid generalization? Neural Comput. 1 1 1989 151-160
4. A. Blum R.L. Rivest Training a 3-node neural network is NP-complete Neural Networks 5 1 1992 117-128
5. S.E. Fahlman, An empirical study of learning speed in backpropagation networks, Technical Report, CMU-CS-88-162, Carnegie-Mellon University, 1988.
6. S.E. Fahlman C. Lebiere The cascade-correlation learning architecture in: D.S. Touretzky (Ed.) Advances in Neural Information Processing Systems vol. 2 1990 Morgan Kaufmann Publishers CA 524-532
7. S.-U. Guan S. Li Incremental learning with respect to new incoming input attributes Neural Process. Lett. 14 3 2001 241-260
8. S.-U. Guan P. Li Incremental learning in terms of output attributes J Intell. Systems 13 2 2004 95-122
9. S.-U. Guan J. Liu Incremental ordered neural network training J. Intell. Systems 12 3 2002 137-172
10. S.-U. Guan J. Liu Incremental neural network training with an increasing input dimension J Intell. Systems 13 1 2004 45-70
11. R.A. Jacobs M.I. Jordan et al. Adaptive mixtures of local experts Neural Comput. 3 1 1991 79-87
12. T.Y. Kwok D.Y. Yeung Objective functions for training new hidden units in constructive neural networks IEEE Trans. Neural Networks 8 5 1997 1131-1148
13. J. Lampinen, A. Vehtari, Bayesian approach for neural networks, Neural Networks April (2001) 7-24
14. M. Lehtokangas Modelling with constructive backpropagation Neural Networks 12 1999 707-716
15. P. Liang, Problem decomposition and subgoaling in artificial neural networks, IEEE International Conference on Systems, Man and Cybernetics, Los Angeles, CA, 1990, pp.178-181.
16. D.J.C. Mackay, Bayesian methods for adaptive models, Ph.D. Thesis, California Institute of Technology, 1991.
17. D.J.C. Mackay A practical bayesian framework for backpropagation Neural Comput. 4 1992 448-472
18. T. Poggio F. Girosi Regularization algorithms for leaning that are equivalent to multi-layer networks Science 247 1990 978-982
19. L. Prechelt, PROBEN1: A set of neural network benchmark problems and benchmarking rules, Technical Report 21/94, Department of Informatics, University of Karlsruhe, Germany, 1994.
20. L. Prechelt Investigation of the CasCor family of learning algorithms Neural Networks 10 5 1997 885-896
21. R. Reed Pruning algorithm - a survey IEEE Trans. Neural Networks 4 5 1993 740-747
22. M. Riedmiller, H. Braun, A direct adaptive method for faster backpropagation learning: The RPROP algorithm, Proceedings of the IEEE International Conference on Neural Networks, 1993, pp.586-591
23. S.G. Romaniuk L.O. Hall Divide and conquer neural networks Neural Networks V6 1993 1105-1116
24. D.E. Rumelhart G. Hinton R. Williams Learning internal representations by error propagation in: D.E. Rumelhart J.L. McClelland (Eds.) Parallel Distributed Processing, Foundations vol. I 1986 MIT Press Cambridge, MA 318-362
25. A.J.C. Sharkey Modularity, combining and artificial neural nets Connect. Sci. 9 1 1997 3-10
26. S. Sjogaard, Generalization in cascade-correlation networks, Proceedings of the IEEE Signal Processing Workshop, 1992, pp. 59-68
27. C.S. Squires, J.W. Shavlik, Experimental analysis of aspects of the cascade-correlation learning architecture, Machine Learning Research Group Working Paper 91-1, Computer Science Department, University of Wisconsin-Madison, 1991
28. T. Tollenaere Supersab: Fast adaptive backpropagation with good scaling properties Neural Networks 3 5 1990 561-573
29. J. Torresen O. Landsvek A review of parallel implementations of backpropagation neural networks in: N. Sundararajan P. Saratchandran (Eds.) Parallel Architectures for Artificial Neural Networks: Paradigms and Implementations 1998 IEEE Computer Society Press Los Alamitos, California 25-63
30. J. Yang, V. Honavar, Experiments with cascade-correlation algorithm, Technical Report 91-16, Department of Computer Science, Iowa State University, 1991.
31. D.Y. Yeung, A neural network approach to constructive induction, Proceedings of the Eighth International Workshop on Machine Learning, Evanston, Illinois, USA, 1991.