Constructive neural network algorithms that solve highly non-separable problems

Studies in Computational Intelligence

Volumn 258, Issue , 2009, Pages 49-70

  Grochowski, Marek ^a   Duch, Włodzisław ^a  

^a NICOLAUS COPERNICUS UNIVERSITY   (Poland)

Author keywords

Boolean functions; Constructive neural networks; Non separable problems; Projection pursuit

Indexed keywords

EID: 74049095160     PISSN: 1860949X     EISSN: None     Source Type: Book Series    
DOI: 10.1007/978-3-642-04512-7_3     Document Type: Conference Paper

References (33)

1. Asuncion, A., Newman, D.: UCI repository of machine learning databases (2007), http://www.ics.uci.edu/?mlearn/MLRepository.html
2. Bengio, Y., Delalleau, O., Roux, N.L.: The curse of dimensionality for local kernel machines. Technical Report 1258, D́partement d'informatique et recherche oṕerationnelle, Universit́e de Montŕeal (2005)
3. Duch, W.: K-separability. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol.4131, pp. 188-197. Springer, Heidelberg (2006)
4. Duch, W.: Towards comprehensive foundations of computational intelligence. In: Duch, W.,Mandziuk, J. (eds.) Challenges for Computational Intelligence, vol.63, pp. 261-316. Springer, Heidelberg (2007)
5. Duch,W., Adamczak, R., Gra̧bczewski, K.: A new methodology of extraction, optimization and application of crisp and fuzzy logical rules. IEEE Transactions on Neural Networks 12, 277-306 (2001)
6. Duch, W., Grudzínski, K.: Meta-learning via search combined with parameter optimization. In: Rutkowski, L., Kacprzyk, J. (eds.) Advances in Soft Computing, pp. 13-22. Physica Verlag, Springer, New York (2002)
7. Duch, W., Jankowski, N.: Survey of neural transfer functions. Neural Computing Surveys 2, 163-213 (1999)
8. Duch, W., Jankowski, N.: Taxonomy of neural transfer functions. In: International Joint Conference on Neural Networks, Como, Italy, vol.III, pp. 477-484. IEEE Press, Los Alamitos (2000)
9. Duch, W., Jankowski, N.: Transfer functions: hidden possibilities for better neural networks. In: 9th European Symposium on Artificial Neural Networks, Brusells, Belgium, pp. 81-94. De-facto publications (2001)
10. Friedman, J.H.: Exploratory projection pursuit. Journal of the American Statistical Association 82, 249-266 (1987)
11. Friedman, J.H., Tukey, J.W.:A projection pursuit algorithm for exploratory data analysis. IEEE Trans. Comput. 23(9), 881-890 (1974)
12. Grochowski, M., Duch, W.: A Comparison of Methods for Learning of Highly Nonseparable Problems. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol.5097, pp. 566-577. Springer, Heidelberg (2008)
13. Grochowski, M., Jankowski, N.: Comparison of instance selection algorithms II. Results and comments. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol.3070, pp. 580-585. Springer, Heidelberg (2004)
14. Haykin, S.: Neural Networks-A Comprehensive Foundation. Maxwell MacMillian Int., New York (1994)
15. Huber, P.J.: Projection pursuit. Annals of Statistics 13, 435-475 (1985), http://www.stat.rutgers.edu/?rebecka/Stat687/huber.pdf
16. Iyoda, E.M., Nobuhara, H., Hirota, K.: A solution for the n-bit parity problem using a single translated multiplicative neuron. Neural Processing Letters 18(3), 233-238 (2003)
17. Jankowski, N., Grochowski, M.: Comparison of instance selection algorithms. i. algorithms survey. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol.3070, pp. 598-603. Springer, Heidelberg (2004) (Pubitemid 38835886)
18. Jones, C., Sibson, R.:What is projection pursuit. Journal of the Royal Statistical Society A 150, 1-36 (1987)
19. Kohonen, T.: Self-organizing maps. Springer, Heidelberg (1995)
20. Kordos,M., Duch,W.:Variable Step Search MLP TrainingMethod. International Journal of Information Technology and Intelligent Computing 1, 45-56 (2006)
21. Liu, D., Hohil, M., Smith, S.: N-bit parity neural networks: new solutions based on linear programming. Neurocomputing 48, 477-488 (2002)
22. Maass, W., Markram, H.: Theory of the computational function of microcircuit dynamics. In: Grillner, S., Graybiel, A.M. (eds.) Microcircuits,The Interface between Neurons and Global Brain Function, pp. 371-392. MIT Press, Cambridge (2006)
23. Marchand, M., Golea, M.: On learning simple neural concepts: from halfspace intersections to neural decision lists. Network: Computation in Neural Systems 4, 67-85 (1993)
24. Mascioli, F.M.F., Martinelli, G.: A constructive algorithm for binary neural networks: The oil-spot algorithm. IEEE Transactions on Neural Networks 6(3), 794-797 (1995)
25. Muselli, M.: On sequential construction of binary neural networks. IEEE Transactions on Neural Networks 6(3), 678-690 (1995)
26. Muselli, M.: Sequential constructive techniques. In: Leondes, C. (ed.) Optimization Techniques,of Neural Network Systems, Techniques and Applications, vol.2, pp. 81-144. Academic Press, San Diego (1998)
27. Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes: The Art of Scientific Computing. Cambridge University Press, Cambridge (2007)
28. Sahami,M.: Learning non-linearly separable boolean functions with linear threshold unit trees and madaline-style networks. In: National Conference on Artificial Intelligence, pp. 335-341 (1993)
29. Shakhnarovish, G., Darrell, T., Indyk, P. (eds.): Nearest-Neighbor Methods in Learning and Vision. MIT Press, Cambridge (2005)
30. Stork, D.G., Allen, J.: How to solve the n-bit parity problem with two hidden units. Neural Networks 5, 923-926 (1992)
31. Wilamowski, B., Hunter, D.: Solving parity-n problems with feedforward neural network. In: Proc. of the Int. Joint Conf. on Neural Networks (IJCNN 2003), vol.I, pp. 2546-2551. IEEE Computer Society Press, Los Alamitos (2003)
32. Young, S., Downs, T.: Improvements and extensions to the constructive algorithm carve. In: Vorbrüggen, J.C., von Seelen,W., Sendhoff, B. (eds.) ICANN 1996. LNCS, vol.1112, pp. 513-518. Springer, Heidelberg (1996)
33. Zollner, R., Schmitz, H.J., Wünsch, F., Krey, U.: Fast generating algorithm for a general three-layer perceptron. Neural Networks 5(5), 771-777 (1992)