Training a feed-forward network with incomplete data due to missing input variables

Applied Soft Computing Journal

Volumn 3, Issue 1, 2003, Pages 23-36

  Brouwer, Roelof K ^a   Pedrycz, Witold ^b  

^a UNIVERSITY OF ALBERTA   (Canada)

^b THOMPSON RIVERS UNIVERSITY   (Canada)

Author keywords

Clustering; Data segmentation; Feed forward neural networks; Incomplete training data; Many valued functions; Missing inputs; One to many mappings; Relations

Indexed keywords

DATA REDUCTION; FUNCTIONS; GRAPHIC METHODS; MATHEMATICAL MODELS; PARAMETER ESTIMATION; PERSONNEL TRAINING; SOFTWARE ENGINEERING;

CLUSTERING; DATA SEGMENTATION; FEED FORWARD NEURAL NETWORKS; INCOMPLETE TRAINING DATA; MANY-VALUED FUNCTION; MISSING INPUTS; ONE-TO-MANY MAPPING; RELATIONS;

NEURAL NETWORKS;

EID: 15944404250     PISSN: 15684946     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1568-4946(03)00003-6     Document Type: Article

References (12)

1. C.M. Bishop, Mixture Density Networks, NCRG/94/004, Available at http://www.ncrg.aston.ac.uk.
2. C.M. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
3. R.K. Brouwer, Training a feed-forward network by feeding gradients forward rather than by back-propagation of errors, Neurocomputing 16 (1997) 117-126.
4. R.A. Jacobs, M.I. Jordan, S.J. Nowlan, G.E. Hinton, Adaptive mixtures of local experts, Neural Comput. 3 (1991) 79-87.
5. H. Kazuyuki, S. Yoshizawa, Recalling of many-valued functions by successive iteration on bottleneck networks, in: Proceedings of the 5th International Conference on Neural Information Processing (ICONTP'98), 1998.
6. K. Lee, T. Lee, Design of neural networks for multi-value regession, in: Proceedings of the International Joint Conference on Neural Networks, 2001, pp. 93-98.
7. T. Plate, Avoiding roundoff error in backpropagating derivatives, in: G.B. Orr, K. Muller (Eds.), Neural Networks: Tricks of the Trade.
8. D. Pountain, The Joy of J, Byte September 1995.
9. D.E. Rumelhart, J.L. McClelland, Learning internal representations by error propagation, in: Parallel Distributed Processing, MIT Press, Boston, 1986, pp. 318-364.
10. Y. Tomikawa, K. Nakayama, Approximating many valued mappings using a recurrent neural network, in: Proceedings of 1998 IEEE World Congress on Computational Intelligence, 1998.
11. Y. Uno, N. Fukumura, R. Suzuki, M. Kawato, A computational model for recognizing objects and planning hand shapes in grasping movements, Neural Networks 8 (6) (1995) 839-852.
12. P.J. Werbos, Beyond regression: new tools for prediction and analysis in the behavioral sciences, doctoral dissertation, Applied Mathematics, Harvard University, Mass., 1974.