Incremental neural network training with an increasing input dimension

Journal of Intelligent Systems

Volumn 13, Issue 1, 2004, Pages 45-69

  Guan, Sheng Uei ^a   Liu, Jun ^a  

^a NATIONAL UNIVERSITY OF SINGAPORE   (Singapore)

Author keywords

Feedforward network; Incremental training; Input attributes; Input dimension; Neural networks; Supervised learning

Indexed keywords

ALGORITHMS; COMPUTER ARCHITECTURE; DATA REDUCTION; LEARNING SYSTEMS; PROBLEM SOLVING; REGRESSION ANALYSIS;

INCREMENTAL TRAINING; INPUT ATTRIBUTES; INPUT DIMENSIONS; SUPERVISED TRAINING;

FEEDFORWARD NEURAL NETWORKS;

EID: 2442628430     PISSN: 03341860     EISSN: None     Source Type: Journal    
DOI: 10.1515/JISYS.2004.13.1.71     Document Type: Article

References (9)

1. Guan, S.U. and Li, S.C. 2001. Incremental learning with respect to new incoming input attributes, Neural Processing Letters, 14, 241-260.
2. Jacobs, R.A., Jordan, M.I., Nowlan, M.I. and Hinton, G.E. 1991. Adaptive mixtures of local experts, Neural Computation, 3, 79-87.
3. Jensen, C.A., El-Sharkawi, M.A. and Marks II, R.J. 2001. Power system security assessment using neural networks: feature selection using Fisher discrimination, IEEE Transactions on Power Systems, 16.
4. Lehtokangas, M. 1999. Modelling with constructive backpropagation, Neural Networks, 12, 707-716.
5. Li, S., Guan, S.U. and Yeo, Ye-Chuan. 2001. Incremental self-growing neural networks with the changing environment, Journal of Intelligent Systems, 11, 43-74.
6. Liu, D., Chang, T.S. and Zhang, Y. 2001. A new learning algorithm for feedforward neural networks, Proceeding of the 2001 IEEE International Symposiumon Intelligent Control, September 5-7, México City, México.
7. Polikar, R., Udpa, L., Udpa, S.S. and Honavar, V. 2001. Learn++: an incremental learning algorithm for supervised neural networks, IEEE Transactions on Systems, Man and Cybernetics - Part C: Applications and Reviews, 31.
8. Prechelt, L. 1994. PROBEN1: A set of neural network benchmark problems and benchmarking rules, Technical Report 21/94, Department of Informatics, University of Karlsruhe, Germany.
9. Riedmiller, M. and Braun, H. 1993. A direct adaptive method for faster backpropagation learning: the RPROP algorithm, in Proceedings of the IEEEInternational Conference on Neural Networks, 586-591.