Investigation of the CasCor family of learning algorithms

Neural Networks

Volumn 10, Issue 5, 1997, Pages 885-896

  Prechelt, Lutz ^a  

^a UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

Additive learning; Cascade correlation; Constructive learning; Cross validation; Empirical study

Indexed keywords

CASCADE CORRELATIONS (CASCOR);

CORRELATION METHODS; ERROR CORRECTION; LEARNING ALGORITHMS; LEARNING SYSTEMS; REGRESSION ANALYSIS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL;

EID: 0031193357     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00115-3     Document Type: Article

References (26)

1. Ash, T. (1989). Dynamic node creation in backpropagation networks. Connection Science, 1 (4), 365-375.
2. Baffes, P.T. & Zelle, J.M. (1992). Growing layers of perceptrons: Introducing the Extentron algorithm. In Proceedings of the International Joint Conference on Neural Networks 1992, Baltimore, Vol. 2 (pp. 392-397). Piscataway, NJ: IEEE.
3. Cun, Y.L., Denker, J.S., & Solla, S.A. (1990). Optimal brain damage. In D.S. Touretzky (Ed.), Advances in Neural Information Processing Systems, Vol. 2 (pp. 598-605). San Mateo, CA: Morgan Kaufman.
4. Fahlman, S.E., & Lebiere, C. (1990). The Cascade-Correlation learning architects. Technical Report CMU-CS-90-100, Pittsburgh, PA: School of Computer Science, Carnegie Mellon University.
5. Finnoff, W., Hergert, F. & Zimmermann, H.G. (1993). Improving model selection by non-convergent methods. Neural Networks, 6, 771-783.
6. Frean, M. (1990). The Upstart algorithm: A method for constructing and training feed-forward neural networks. Neural Computation, 2, 198-209.
7. Fritzke, B. (1994). Growing cell structures - a self-organizing network for unsupervised and supervised learning. Neural Networks, 7 (9), 1441-1460.
8. Gallant, S.I. (1986). Three constructive algorithms for network learning. In Proceedings of the 8th Annual Conference of the Cognitive Science Society (pp. 652-660).
9. Geman, S., Bienenstock, E. & Doursat, R. (1992). Neural networks and the bias/variance dilemma. Neural Computation, 4, 1-58.
10. Hanson, S.J. (1990). Meiosis networks. In D.S. Touretzky (Ed.), Advances in Neural Information Processing Systems, Vol. 2 (pp. 533-541). San Mateo, CA: Morgan Kaufman.
11. Hassibi, B., & Stork, D.G. (1993). Second order derivatives for network pruning: Optimal brain surgeon. In S.J. Hanson, J.D. Cowan, & C.L. Giles (Eds.), Advances in Neural Information Processing Systems, Vol. 5 (pp. 164-171). San Mateo, CA: Morgan Kaufman.
12. Krogh, A., & Hertz, J.A. (1992). A simple weight decay can improve generalization. In J.E. Moody, S.J. Hanson, & R.P. Lippmann (Eds.), Advances in Neural Information Processing Systems, Vol. 4 (pp. 950-957). San Mateo, CA: Morgan Kaufman.
13. Levin, A.U., Leen, T.K., & Moody, J.E. (1994). Fast pruning using principal components. In J.D. Cowan, G. Tesauro, & J. Alspector (Eds.), Advances in Neural Information Processing Systems, Vol. 6 (pp. 35-42). San Mateo, CA: Morgan Kaufman.
14. Littmann, E., & Ritter, H. (1992). Cascade network architectures. In Proceedings of the International Joint Conference on Neural Networks, Baltimore, Vol. 2 (pp. 398-404). Piscataway, NJ: IEEE.
15. Littmann, E., & Ritter, H. (1993). Generalization abilities of cascade network architectures. In S.J. Hanson, J.D. Cowan, & C.L. Giles (Eds.), Advances in Neural Information Processing Systems, Vol. 5 (pp. 188-195). San Mateo, CA: Morgan Kaufman.
16. Mézard, M. & Nadal, J.-P. (1989). Learning in feedforward layered networks: The Tiling algorithm. Journal of Physics A: Math. Gen., 22 (12), 2191-2203.
17. Nowlan, S.J. & Hinton, G.E. (1992). Simplifying neural networks by soft weight-sharing. Neural Computation, 4 (4), 473-493.
18. Prechelt, L. (1994). PROBEN1 - A set of benchmarks and benchmarking rules for neural network training algorithms. Technical Report 21/94, Fakultät für Informatik, Universität Kaxlsruhe, Germany. Anonymous FTP:/pub/papers/techreports/1994/1994-21.ps.gz on ftp.ira.uka.de.
19. Reed, R. (1993). Pruning algorithms - a survey. IEEE Transactions on Neural Networks, 4 (5), 740-746.
20. Riedmiller, M., & Braun, H. (1993). A direct adaptive method for faster backpropagation learning: The RPROP algorithm. In Proceedings of the IEEE International Conference on Neural Networks, San Francisco, Vol. XX (pp. 586-591). Piscataway, NJ: IEEE.
21. Simon, N. (1993). Constructive supervised learning algorithms for artificial neural networks. Master's thesis. Delft University of Technology, Department of Electrical Engineering, Delft, Netherlands.
22. Sjøgaard, S. (1991). A Conceptual Approach to Generalisation in Dynamic Neural Networks. Doctoral thesis, Aarhus University, Aarhus, Danmark.
23. Wang, Z., Massimo, C.D., Tham, M.T. & Morris, A.J. (1994). A procedure for determining the topology of multilayer feedforward neural networks. Neural Networks, 7 (2), 291-300.
24. Wynne-Jones, M. (1991). Node splitting: A constructive algorithm for feed-forward neural networks. In J.E. Moody, S.J. Hanson, & R.P. Lippmann (Eds.), Advances in Neural Information Processing Systems, Vol. 4 (pp. 1072-1079). San Mateo, CA: Morgan Kaufman.
25. Yeung, D.-Y. (1991). A neural network approach to constructive induction. In A. Lawrence, & G.C.C. Birnbaum (Eds.), Machine Learning - Proceedings of the 8th International Workshop (pp. 228-232). San Mateo, CA: Morgan Kaufman.
26. Zollner, R., Schmitz, H.J., Wünsch, F. & Krey, U. (1992). Fast generating algorithm for a general three-layer perceptron. Neural Networks, 5 (5), 771-777