Universal approximation capability of cascade correlation for structures

Neural Computation

Volumn 17, Issue 5, 2005, Pages 1109-1159

  Hammer, Barbara ^a   Micheli, Alessio ^b   Sperduti, Alessandro ^c  

^a CLAUSTHAL UNIVERSITY OF TECHNOLOGY   (Germany)

^b UNIVERSITY OF PISA   (Italy)

^c UNIVERSITY OF PADOVA   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 17444403164     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/0899766053491878     Document Type: Article

References (42)

1. Alquezar, R., & Sanfeliu, A. (1995). An algebraic framework to represent finite state machines in single-layer recurrent neural networks. Neural Computation, 7(5), 931-949.
2. Baldi, P., Brunak, S., Frasconi, P., Pollastri, G., & Soda, G. (1999). Exploiting the past and future in protein secondary structure prediction. Bioinformatics, 25(11), 937-946.
3. Bengio Y., & Frasconi, P. (1996). Input/output HMMs for sequence processing. IEEE Transactions on Neural Networks, 7(5), 1231-1249.
4. Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157-166.
5. Bianucci, A. M., Micheli, A., Sperduti, A., & Starita, A. (2000). Application of cascade correlation networks for structures to chemistry. Journal of Applied Intelligence, 12, 117-146.
6. de Mauro, C., Diligenti, M., Gori, M., & Maggini, M. (2003). Similarity learning for graph-based image representations. Pattern Recognition Letters, 24(8), 1115-1122.
7. Diligenti, M., Frasconi, P., & Gori, M. (2003). Hidden tree Markov models for document image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(4), 519-523.
8. Fahlmann, S. E. (1991). The recurrent cascade-correlation architecture. In R. P. Lippmann, J. E. Moody, & D. S. Touretzky (Eds.), Advances in neural information processing systems, 3 (pp. 190-196). San Mateo, CA: Morgan Kaufmann.
9. Fahlmann, S. E., & Lebiere, C. (1990). The cascade-correlation learning architecture. In D. S. Touretzky (Ed.), Advances in neural information processing systems 2 (pp. 524-532). Son Mateo, CA: Morgan Kaufmann.
10. Forcada, M. L., & Carrasco, R. C. (1995). Learning the initial state of a second order recurrent neural network during regular language inference. Neural Computation, 7(5), 923-949.
11. Frasconi, P. (2002). Comparing convolution kernels and RNNs on a wide-coverage computational analysis of natural language. NIPS 2002 workshop.
12. Frasconi, P., & Gori, M. (1996). Computational capabilities of local-feedback recurrent networks acting as finite-state machines. IEEE Transactions on Neural Networks, 7(6), 1521-1524.
13. Frasconi, P., Gori, M., & Sperduti, A. (1998). A general framework of adaptive processing of data structures. IEEE Transactions on Neural Networks, 9(5), 768-786.
14. Funahashi K., & Nakamura, Y. (1993). Approximation of dynamical systems by continuous time recurrent neural networks. Neural Networks, 6(6), 801-806.
15. Giles, C. L., Chen, D., Sun, G. Z., Chen, H. H., Lee, Y. C., & Goudreau, M. W. (1995). Constructive learning of recurrent neural networks: Limitations of recurrent cascade correlation and a simple solution. IEEE Transactions on Neural Networks, 6(4), 829-836.
16. Goller, C. (1997). A connectionist approach for learning search control heuristics for automated deduction systems. Unpublished doctoral dissertation, Technische Universität München.
17. Goller, C., & Küchler, A. (1996). Learning task-dependent distributed structure-representations by backpropagation through structure. In IEEE International Conference on Neural Networks (pp. 347-352). Piscataway, NJ: IEEE Computer Society Press.
18. Hammer, B. (2000). Learning with recurrent neural networks. Berlin: Springer.
19. Hammer, B. (2001). Generalization ability of folding networks. IEEE Transactions on Knowledge and Data Engineering, 13(2), 196-206.
20. Hammer, B., & Steil, J. J. (2002). Perspectives on learning with recurrent neural networks. In M. Verleysen (Ed.), ESANN'02 (pp. 357-368). Brussels: D-side Publications.
21. Haussler, D. (1999). Convolution kernels on discrete structure (Tech. Rep.). Santa Cruz: University of California at Santa Cruz.
22. Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2, 359-366.
23. Jaakkola, T., Diekhans, M., & Haussler, D. (2000). A discriminative framework for detecting remote protein homologies. Journal of Computational Biology, 7, 95-114.
24. Kremer, S. (2001). Spatio-temporal connectionist networks: A taxonomy and review. Neural Computation, 13(2), 249-306.
25. Leslie, C., Eskin, E., & Noble, W. (2002). The spectrum kernel: A string kernel for SVM protein classification. In Proc. Pacific Symposium on Biocomputing (pp. 564-575). Available online: http://psb.stanford.edu/psb. online/.
26. Lodhi, H., Shawe-Taylor, J., Cristianini, N., & Watkins, C.J.C.H. (2000). Text classification using string kernels. In S. A. Solla, T. K. Leen, & K.-R. Müller (Eds.), Advances in information processing systems, 12 (pp. 563-569). Cambridge, MA: MIT Press.
27. Micheli, A. (2003) Recursive processing of structured domains in machine learning. Unpublished doctoral dissertation, University of Pisa.
28. Micheli, A., Sona, D., & Sperduti, A. (2000). Bi-causal recurrent cascade correlation. In Proceedings of the International Joint Conference on Neural Networks, (Vol. 3, pp. 3-8). Piscataway, NJ: IEEE Computer Society Press.
29. Micheli, A., Sona, D., & Sperduti, A. (2002). Recursive cascade correlation for contextual processing of structured data, In Proceedings of the International Joint Conference on Neural Networks 2002, 1 (pp. 268-273). N. P.
30. Micheli, A., Sona, D., & Sperduti, A. (2003). Formal definition of context in contextual recursive cascade correlation networks. In E. Alpaydin, E. Oja, & L. Xu (Eds.), Proceedings of ICANN/ICONIP 2003, LNCS 2714 (pp. 173-130). Berlin: Springer.
31. Micheli, A., Sona, D., & Sperduti, A. (In press). Contextual processing of structured data by recursive cascade correlation. IEEE Transactions on Neural Networks.
32. Pollastri, G., Baldi, P., Vullo, A., & Frasconi, P. (2002). Prediction of protein topologies using GIOHMMs and GRNNs. In T. G. Dietterich, S. Becker, & Z. Ghahramani (Eds.), Advances in neural information processing systems, 14. Cambridge, MA: MIT Press.
33. Scarselli, F., & Tsoi, A. C. (1998). Universal approximation using feedforward neural networks: A survey of some existing methods, and some new results. Neural Networks, 11, 15-37.
34. Sontag, E. D. (1992). Feedforward nets for interpolation and classification. Journal of Computer and System Sciences, 45, 20-48.
35. Sperduti, A. (1997). On the computational power of neural networks for structures. Neural Networks, 10(3), 395-400.
36. Sperduti, A., Majidi, D., & Starita, A. (1996). Extended cascade-correlation for syntactic and structural pattern recognition. In P. Perner, P. Wand, & A. Rosenfeld (Eds.), Advances in structured and syntactical pattern recognition (pp. 90-99). New York: Springer.
37. Sperduti, A., & Starita, A. (1997). Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks, 8(3), 714-735.
38. Sturt, P., Costa, F., Lombardo, V., & Frasconi, P. (2003). Learning first-pass structural attachment preferences with dynamic grammars and recursive neural networks. Cognition, 88(2), 133-169.
39. Sun, R. (2001). Introduction to sequence learning. In R. Sun & C. L. Giles (Eds.), Sequence learning: Paradigms, algorithms, and applications (pp. 1-10), New York: Springer.
40. Vullo, A., & Frasconi, P. (2003). A recursive connectionist approach for predicting disulfide connectivity in proteins. In Proceedings of the Eighteenth Annual ACM Symposium on Applied Computing (SAC 2003). Melbourne, FL.
41. Watkins, C. (1999). Dynamic alignment kernels (Tech. Rep.). Royal Holloway, University of London.
42. Wakuya, H., & Zurada, J. (2001). Bi-directional computing architectures for time series prediction. Neural Networks, 14, 1307-1321.