MLP iterative construction algorithm

Neurocomputing

Volumn 17, Issue 3-4, 1997, Pages 195-216

  Rathbun, Thomas F ^b   Rogers, Steven K ^a   DeSimio, Martin P ^b   Oxley, Mark E ^b  

^a BATTELLE MEMORIAL INSTITUTE   (United States)

^b NONE

Author keywords

Construction; Hidden node pruning; Ho Kashyap method; Multi layered perceptron; Neural network training

Indexed keywords

ALGORITHMS; BACKPROPAGATION; COMPUTER ARCHITECTURE; ITERATIVE METHODS; PROBLEM SOLVING;

HIDDEN NODE PRUNING;

NEURAL NETWORKS;

ARCHITECTURE; ARTICLE; COMPUTER; COMPUTER SYSTEM; LEARNING; NERVE CELL NETWORK; PRIORITY JOURNAL;

EID: 0031282102     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(97)00054-4     Document Type: Article

References (20)

1. E.B. Baum, On the capabilities of multilayer preceptrons, J. Complexity 4 (1988) 193-215.
2. E.B. Baum, What size net gives valid generalization, Neural Computation 1 (1989) 151-160.
3. E.B. Baum, D. Haussler, What size net gives valid generalization, Neural Comput. 1 (1) (1989) 151-160.
4. N. Burgess, A constructive algorithm that converges for real-valued input patterns, J. Neural Systems 5 (1) (1994) 59-66.
5. Cover, M. Thomas, Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition, IEEE Trans. Electronic Comput. 22 (3) (1965) 326-334.
6. G. Cybenko, Approximation by superposition of sigmoidal functions, Math. Control Signals Systems 2 (1989) 303-314.
7. R.O. Duda, E.H. Peter, Pattern Classification and Scene Analysis, Wiley, New York, 1973.
8. S.E. Fahlman, L. Christian, The cascade-correlation learning architecture, in: D.S. Touretzky (Eds.), Advances in Neural Information Processing Systems, vol. 2, San Mateo, Morgan Kaufmann, CA, 1990, pp. 524-532.
9. A.K. Jain, M. Jianchang, Neural networks and pattern recognition, in: J.M. Zurada, et al. (Eds.), Computational Intelligence Imitating Life, Chap. 4, IEEE Press, New York, 1994, pp. 194-212.
10. V. Kumar, et al., Introduction to Parallel Computing: Design and Analysis of Parallel Algorithms, Benjamin/Cummings, Menlo Park, CA, 1994.
11. K.L. Priddy, Feature extraction and classification of FLIR imagery using relative locations of non-homogeneous regions with feedforward neural networks, Ph.D. dissertation, Air Force Institute of Technology, WPAFB, OH, 1992.
12. R. Reed, Pruning algorithms - a survey, Neural Networks 4 (5) (1993) 740-747.
13. A. Roy, et al., An algorithm to generate radial basis functions (RBF)-like nets for classification problems, Neural Networks 8 (2) (1995) 179-201.
14. D.W. Ruck, Characterization of multilayer perceptrons and their application to multisensor automatic target detection, Ph.D. dissertation, Air Force Institute of Technology, WPAFB, OH, 1990.
15. D.W. Ruck, R. Steven, Feature selection using a multilayer perceptron, J. Neural Network Comput. (Fall 1990) 40-48.
16. E.D. Sontag, Sigmoids distinguish more efficiently than heaviside, Neural Comput. 1 (1989) 470-472.
17. E.D. Sontag, Feedforward nets for interpolation and classification, J. Comput. Systems Sci. 45 (1992) 20-48.
18. G.L. Tarr, Multi-layered feedforward neural networks for image segmentation, Ph.D. dissertation, Air Force Institute of Technology, WPAFB, OH, 1991.
19. V.N. Vapnik, Estimation of Dependences Based on Empirical Data, Springer, New York, 1982.
20. J. Yang et al., M-TILING - A constructive neural network learning algorithm for multi-category pattern classification, In: Proc. World Congress on Neural Networks, vol. 961, INNS Press, San Diego, CA, 1996, pp. 182-187.