Classification methodologies of multilayer perceptrons with sigmoid activation functions

Pattern Recognition

Volumn 38, Issue 10, 2005, Pages 1469-1482

  Daqi, Gao ^a,b   Yan, Ji ^a  

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

^b EAST CHINA UNIVERSITY OF SCIENCE AND TECHNOLOGY   (China)

Author keywords

Empirical formula; Generalization; Hidden nodes; Multilayer perceptrons; Sigmoid activation functions

Indexed keywords

DECISION THEORY; MATHEMATICAL TRANSFORMATIONS; MATRIX ALGEBRA; MULTILAYER NEURAL NETWORKS; PATTERN RECOGNITION; PROBLEM SOLVING;

EMPIRICAL FORMULA; GENERALIZATION; HIDDEN MODES; SIGMOID ACTIVATION FUNCTIONS;

CLASSIFICATION (OF INFORMATION);

EID: 22844434823     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patcog.2005.03.024     Document Type: Article

References (28)

1. R.P. Lippmann Pattern classification using neural networks IEEE Commun. Mag. 11 1989 47 64
2. M.L. Vaughn Derivation of the multilayer perceptron weight constraints for direct network interpretation and knowledge discovery Neural Networks 12 1999 1259 1271
3. K. Funahashi Multilayer neural networks and Bayes decision theory Neural Networks 11 1998 209 213
4. G.J. Gibson, and C.F.N. Cowan On the decision regions of multilayer perceptrons Proc. IEEE 78 9 1990 1590 1594
5. C.M. Bishop Neural Networks for Pattern Recognition 1995 Clarendon Press Oxford
6. A. Lapedes, and R. Farber How neural nets work D. Anderson Neural Information Processing Systems 1988 American Institute of Physics New York 442 456
7. S.C. Huang, and Y.F. Huang Bounds on the number of hidden neurons in multilayer perceptrons IEEE Trans. Neural Networks 2 1 1991 47 55
8. G.B. Huang, Y.Q. Chen, and H.A. Babri Classification ability of single hidden layer feedforward neural networks IEEE Trans. Neural Networks 11 3 2000 799 801
9. K.J. Lang, M.J. Witbrock, Learning to tell two spirals apart, Proc. Connect. Model Summer School, San Mateo, CA, Morgan Kauffman, 1989, pp. 52-58.
10. S. Ridella, S. Rovetta, and R. Zunino Circular backpropagation networks for classifications IEEE Trans. Neural Networks 8 1 1998 84 97
11. S. Draghici On the capabilities of neural networks using limited precision weights Neural Networks 15 2002 395 414
12. R.P. Gormann, and T.J. Sejnowski Analysis of hidden units in a layered network trained to classify sonar targets Neural Networks 1 1988 75 89
13. M. Gori, and F. Scarselli Are multilayer perceptrons adequate for pattern recognition and verification? IEEE Trans. Pattern Anal. Mech. Intell. 20 11 1998 851 859
14. G.B. Huang, and H.A. Babri Upper bounds of the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions IEEE Trans. Neural Networks 9 1 1998 224 228
15. D. Chakraborty, and N.R. Pal A novel training scheme for multilayered perceptrons to realize proper generalization and incremental learning IEEE Trans. Neural Networks 14 1 2003 1 14
16. E. Levin, N. Tishby, and S.A. Solla A statistical approach to learning and generalization in layered neural networks Proc. IEEE 78 10 1990 1568 1574
17. D.H. Wolpert A mathematical theory of generalization Complex System 4 1990 151 249
18. G. Mirchandani, and W. Cao On hidden nodes for Neural Nets IEEE Trans. Circuits Syst. 36 5 1989 661 664
19. D. Gao, and G. Yang Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks Pattern Recognition 36 4 2003 869 878
20. V.N. Vapnik An overview of statistical learning theory IEEE Trans. Neural Networks 10 5 1999 988 999
21. T. Elloft, and R.J.P. Defigueiredo A new neural network for cluster-detection-and-labeling IEEE Trans. Neural Networks 9 5 1998 1021 1035
22. N.B. Karayiannis Reformulated radial basis neural networks trained by gradient descent IEEE Trans. Neural Networks 10 3 1999 657 671
23. ftp://ftp.ics.uci.edu/pub/mechine-learning-databases or http://www.ics.uci.edu/~mlearn.
24. R.O. Duda, P.E. Hart, and D.G. Stork Pattern Classification second ed. 2000 Wiley New York
25. R.P. Lippmann An introduction to computing with neural nets IEEE ASSP Magazine 4 1987 4 22
26. R.H. Nielsen Counterpropagation networks Appl. Opt. 26 1987 4979 4984
27. S.Y. Kung Digital neural networks 1993 PTR Prentice Hall
28. G. Daqi, and W. Shouyi An optimization method for the topological structures of feedforward multi-layer neural networks Pattern Recognition 31 9 1998 1337 1342