Nonlinear neural network model of mixture of local principal component analysis: application to handwritten digits recognition

Pattern Recognition

Volumn 34, Issue 2, 2001, Pages 203-214

  Zhang, Bailing ^e   Fu, Minyue ^a,b,c   Yan, Hong ^d  

^a UNIVERSITY OF SCIENCE AND TECHNOLOGY OF CHINA   (China)

^b UNIVERSITY OF WISCONSIN MADISON   (United States)

^c Nicolet Instruments   (United States)

^d General Network Corporation   (United States)

^e NONE

Author keywords

[No Author keywords available]

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; FEATURE EXTRACTION; IMAGE RECONSTRUCTION; LEARNING ALGORITHMS; LEAST SQUARES APPROXIMATIONS; MATHEMATICAL MODELS; NEURAL NETWORKS;

HANDWRITTEN DIGIT RECOGNITION; MIXTURE MODEL; NEURAL GAS ALGORITHM; PRINCIPAL COMPONENT ANALYSIS; SUBSPACE PATTERN RECOGNITION;

CHARACTER RECOGNITION;

EID: 0034826327     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(00)00009-1     Document Type: Article

References (24)

1. S. Watanable, N. Pakvasa, Subspace method in pattern recognition, Proceedings of the International Joint Conference on Pattern Recognition, 1973, pp. 25-32.
2. E. Oja, Simplified neuron model as a principal component analyzer, J. Math. Biol. 15 (1982) 267-273.
3. E. Oja, Subspace Methods of Pattern Recognition, Research Studies Press, Letchworth, UK, 1983.
4. E. Oja, Neural networks, principal components and subspace, Int. J. Neural System 1 (1989) 61-68.
5. E. Oja, Principal components, minor components, and linear neural networks, Neural Networks 5 (1992) 927-935.
6. T.D. Sanger, Optimal unsupervised learning in a single-layer linear feedforward neural network, Neural Networks 2 (1989) 459-473.
7. T. Hastie, W. Stuetzle, Principal curves, J. Am. Stat. Assoc. 84 (1989) 502-516.
8. R.D. Dony, S. Haykin, Image segmentation using a mixture of principal components representation, IEE Proc.-Visual Image Signal Process 144 (1997) 73-80.
9. G.E. Hinton, P. Dayan, M. Revow, Modelling the manifolds of images of handwritten digits, IEEE Trans. Neural Networks 8 (1997) 65-74.
10. R.A. Jacobs, M.I. Jordan, S.J. Nowlan, G.E. Hinton, Adaptive mixtures of local experts, Neural Comput. 3 (1991) 79-87.
11. T. Kohonen, Self-organized formation of various invariant-feature filters in the adaptive subspace SOM, Neural Comput. 9 (1997) 1321-1344.
12. N. Kambhatla, T.K. Lee, Dimension reduction by local principal component analysis, Neural Comput. 9 (1997) 1493-1516.
13. T.M. Martinetz, S.G. Berkovich, K.J. Schulten, Neural-gas network for vector quantization and its application to time-series prediction, IEEE Trans. Neural Networks 4 (1993) 558-568.
14. J.L. Marroquin, F. Girosi, Some extensions of the K-means algorithm for image segmentation and pattern classification, MIT Technical Report, AI Memo No. 11390, 1994.
15. K. Rose, E. Gurewitz, G.C. Fox, A deterministic annealing approach to clustering, Phys. Rev. Lett. 11 (1990) 589-594.
16. L. Xu, Least mean square error reconstruction principle for self-organization, Neural Networks 6 (1993) 627-648.
17. J. Karhunen, J. Joutsensalo, Representation and separation of signals using nonlinear PCA type learning, Neural Networks 7 (1994) 113-127.
18. J. Karhunen, J. Joutsensalo, Generalizations of principal component analysis, optimization problems, and neural networks, Neural Networks 8 (1995) 549-562.
19. C.Y. Suen, C. Nadal, R. Legault, T.A. Mai, L. Lam, Computer recognition of unconstrained handwritten numerals, Proc. IEEE 80 (1992) 1162-1180.
20. Y.L. Cun et al., Constrained neural network for unconstrained handwritten digit recognition, Proceedings of the First International Workshop on Frontiers in Handwritting Recognition, Montreal, Canada, 1990, pp. 145-154.
21. Sung-Bae Cho, Neural network classifiers for recognizing totally unconstrained handwritten numerals, IEEE Trans. Neural Networks 8 (1997) 43-53.
22. H. Schwenk, M. Milgram, Transformation invariant autoassociation with application to handwritten character recognition, in: G. Tesauro, D. Touretzky, T. Lee (Eds.), NIPS 7, Morgan Kaufmann, Los Altos, CA, 1995, pp. 991-998.
23. R. Anand et al., Efficient classification for multiclass problems using modular neural networks, IEEE Trans. Neural Networks 6 (1995) 117-124.
24. M. Revow, C.K.I. Williams, G.E. Hinton, Using generative models for handwritten digit recognition, IEEE Trans. Pattern Anal. Machine Intell. 18 (1996) 592-606.