Learning and Generalization in Cascade Network Architectures

Neural Computation

Volumn 8, Issue 7, 1996, Pages 1521-1539

  Littmann, Enno ^a   Ritter, Helge ^b  

^a UNIVERSITY OF ULM   (Germany)

^b BIELEFELD UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; HUMAN; LEARNING; PHYSIOLOGY;

GENERALIZATION (PSYCHOLOGY); HUMANS; LEARNING; NEURAL NETWORKS (COMPUTER);

EID: 0030267612     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/neco.1996.8.7.1521     Document Type: Article

References (32)

1. Atkeson, C. 1992. Memory-based approaches to approximating continuous function. In Nonlinear Modeling and Forecasting, M. Casdagli, and S. Eubank, eds., Vol. XII of SFI Studies in the Sciences of Complexity, pp. 503-521. Addison-Wesley, New York.
2. Baffes, P., and Zelle, J. 1992. Growing layers of perceptrons: Introducing the extentron algorithm. Proc. Int. Joint Conf. Neural Networks, Vol. II, pp. 392-397.
3. Baum, E., and Haussler, D. 1989. What size net gives valid generalization? Neural Comp. 1, 151-160.
4. Cleveland, W., Devlin, S., and Grosse, E. 1988. Regression by local fitting: Methods, properties, and computational algorithms. Nonlinear Model. Forecast. J. Economet. 37, 87-114.
5. Crowder, R. S. 1990. Predicting the Mackey-Glass timeseries with cascade-correlation learning. In Connectionist Models: Proceedings of the 1990 Summer School, D. S. Touretzky, J. L. Elman, T. J. Sejnowski, and G. E. Hinton, eds., pp. 524-532. Morgan Kaufmann, San Mateo, CA.
6. Fahlman, S. E. 1992. Personal communication.
7. Fahlman, S. E., and Lebiere, C. 1990. The cascade-correlation learning architecture. In Advances in Neural Information Processing Systems 2, D. S. Touretzky, ed., pp. 524-532. Morgan Kaufmann, San Mateo, CA.
8. Farmer, J. and Sidorowich, J. 1987. Predicting chaotic time series. Phys. Rev. Lett. 59, 845-848.
9. Frean, M. 1990. The upstart algorithm: A method for constructing and training feedforward neural networks. Neural Comp. 2, 198-209.
10. Friedman, J. H., Bentley, J. L., and Finkel, R. A. 1977. An algorithm for finding best matches in logarithmic expected time. ACM Transact. Math. Software 3, 209-226.
11. Hartmann, E., and Keeler, J. D. 1991. Predicting the future: Advantages of semilocal units. Neural Comp. 3, 566-578.
12. Jacobs, R., Jordan, M., Nowlan, S., and Hinton, G. 1991. Adaptive mixtures of local experts. Neural Comp. 3, 79-87.
13. Kohonen, T. 1982. Self Organization and Associative Memory. Springer Series in Information Sciences 8. Springer-Verlag, Berlin.
14. Kohonen, T. 1988. Statistical pattern recognition with neural networks: Bench-marking studies. Proc. ICNN. IEEE Neural Network Council.
15. Kohonen, T. 1990. The self-organizing map. Proceedings IEEE, 78, 1464-1480.
16. Lapedes, A., and Farber, R. 1987. Nonlinear Signal Processing Using Neural Networks: Prediction and System Modeling. Tech. Rep. TR LA-UP-87-2662, Los Alamos National Laboratory, Los Alamos, NM.
17. LeCun, Y., Denker, J. S., and Solla, S. A. 1990. Optimal brain damage. In Advances in Neural Information Processing Systems 2, D. S. Touretzky, ed., pp. 598-605. Morgan Kaufmann, San Mateo, CA.
18. Littmann, E., and Ritter, H. 1992. Cascade network architectures. Proc. Int. Joint Conf. Neural Networks, Vol. II, pp. 398-404.
19. Littmann, E., and Ritter, H. 1994. Analysis and Applications of the Direct Cascade Architecture. Tech. Rep. TR 94-2, Department of Computer Science, Bielefeld University, Bielefeld, Germany.
20. Mackey, M., and Glass, L. 1977. Oscillations and chaos in physiological control systems. Science 197, 287-289.
21. Mezard, M., and Nadal, J.-P. 1989. Learning in feedforward layered networks: The tiling algorithm. J. Phys. A 22, 2191-2204.
22. Moody, J., and Darken, C. 1988. Learning with localized receptive fields. In Connectionist Models: Proceedings of the 1988 Summer School, pp. 133-143. Morgan Kaufmann, San Mateo, CA.
23. Nabhan, T., and Zomaya, A. 1994. Toward generating neural network structures for function approximation. Neural Networks, 7, 89-99.
24. Nowlan, S. J., and Hinton, G. E. 1991. Evaluation of adaptive mixtures of competing experts. In Advances in Neural Information Processing Systems 5, D. S. Touretzky, ed., Morgan Kaufmann, San Mateo, CA.
25. Omohundro, P. 1991. Bumptrees for efficient function, constraint, and classification learning. In Advances in Neural Information Processing Systems 3, R. P. Lippmann, J. E. Moody, and D. S. Touretzky, eds., pp. 693-699. Morgan Kaufmann, San Mateo, CA.
26. Poggio, T., and Girosi, F. 1990. Regularization algorithms for learning that are equivalent to multilayer networks. Science 247.
27. Ritter, H. 1991. Learning with the self-organizing map. In Artificial Neural Networks 1, T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, eds., pp. 357-364. Elsevier Science Publishers B.V., North Holland.
28. Ritter, H., Martinetz, T., and Schulten, K. 1992. Neural Computation and Self-Organizing Maps: An Introduction. Addison-Wesley, New York. (English and German).
29. Rumelhart, D. E., Hinton, G. E., and Williams, R. J. 1986. Learning representations by back-propagating errors. Nature (London) 323, 533-536.
30. Shepard, D. 1968. A two-dimensional interpolation function for irregularly spaced data. Proc. 23rd Natl. Conf. ACM 517-523.
31. Stokbro, K., Umberger, D., and Hertz, J. 1990. Exploiting neurons with localized receptive fields to learn chaos. Complex Syst. 4, 603-622.
32. Werbos, P. 1974. Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences. Ph.D. thesis, Harvard Univ. Committee of Applied Mathematics, Cambridge, MA.