A preliminary empirical comparison of recursive neural networks and tree kernel methods on regression tasks for tree structured domains

Neurocomputing

Volumn 64, Issue 1-4 SPEC. ISS., 2005, Pages 73-92

  Micheli, Alessio ^a   Portera, Filippo ^b   Sperduti, Alessandro ^b  

^a UNIVERSITY OF PISA   (Italy)

^b UNIVERSITY OF PADOVA   (Italy)

Author keywords

Kernel methods; Kernels for structures; Learning in structured domains; Recursive neural networks

Indexed keywords

DATA ACQUISITION; PROBLEM SOLVING; REGRESSION ANALYSIS;

KERNEL METHODS; QUANTITATIVE STRUCTURE-ACTIVITY RELATIONSHIPS (QSAR); RECURSIVE NEURAL NETWORKS (RECNN); SUPPORT VECTOR REGRESSION (SVR);

NEURAL NETWORKS;

ALKANE DERIVATIVE; AROMATIC HYDROCARBON; BENZODIAZEPINE;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; CALIBRATION; CHEMICAL LABELING; CHEMICAL STRUCTURE; COMPUTER MODEL; COMPUTER SIMULATION; DATA ANALYSIS; DATA BASE; FEEDBACK SYSTEM; INTERMETHOD COMPARISON; LINEAR REGRESSION ANALYSIS; MATHEMATICAL MODEL; MOLECULE; NONHUMAN; PREDICTION; PRIORITY JOURNAL; QUANTITATIVE STRUCTURE ACTIVITY RELATION; QUANTITATIVE STRUCTURE PROPERTY RELATION; REGRESSION ANALYSIS; STRUCTURAL BIOINFORMATICS; TREE; VALIDATION PROCESS;

EID: 15844387278     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.11.013     Document Type: Article

References (31)

1. P. Baldi S. Brunak P. Frasconi G. Pollastri G. Soda Exploiting the past and the future in protein secondary structure prediction Bioinformatics 15 11 1999 937-946
2. P. Baldi G. Pollastri The principled design of large-scale recursive neural network architectures-DAG-RNNs and the protein structure prediction problem J. Mach. Learning Res. 4 2003 575-602
3. L. Bernazzani, C. Duce, A. Micheli, V. Mollica, A. Sperduti, A. Starita, M.R. Tiné, Predicting thermodynamic properties from molecular structures by recursive neural networks, Comparison with classical group contributions methods, Technical Report TR-04-16, Università di Pisa, Dipartimento di Informatica, Pisa, October 2004.
4. A.M. Bianucci A. Micheli A. Sperduti A. Starita Application of cascade correlation networks for structures to chemistry J. Appl. Intell. 12 2000 117-146
5. A.M. Bianucci A. Micheli A. Sperduti A. Starita A novel approach to QSPR/ QSAR based on neural networks for structures in: L.M. Sztandera H.M. Cartwright (Eds.), Soft Computing Approaches in Chemistry March 2003 Springer Heidelberg
6. D. Cherqaoui D. Villemin Use of neural network to determine the boiling point of alkanes J. Chem. Soc. Faraday Trans. 90 1 1994 97-102
7. M. Collins, N. Duffy, Convolution kernels for natural language, in: NIPS 14, MIT Press, Cambridge, MA, 2002.
8. N. Cristianini J. Shawe-Taylor An introduction to Support Vector Machines and other Kernel-based Learning Methods 2000 Cambridge University Press Cambridge
9. M. Diligenti P. Frasconi M. Gori Hidden tree markov models for document image classification IEEE Trans. Pattern Anal. Mach. Intell. 25 4 2003 519-523
10. S. Džeroski N. Lavrač Relational Data Mining September 2001 Springer Berlin
11. P. Frasconi, M. Gori, A. Kuechler, A. Sperduti, From sequences to data structures: Theory and applications, in: A Field Guide to Dynamic Recurrent Networks, Wiley-IEEE Press, 2001, pp. 351-374.
12. T. Gaertner, A survey of kernels for structured data, Newsletter of the ACM Special Interest Group on Knowledge Discovery and Data Mining, vol. 5(1), July 2003, pp. 49-58.
13. D. Hadjipavlou-Litina C. Hansch Quantitative structure-activity relationships of the benzodiazepines, a review and reevaluation Chem. Rev. 94 6 1994 1483-1505
14. B. Hammer Learning with Recurrent Neural Networks in: Springer Lecture Notes in Control and Information Sciences vol. 254 2000 Springer Berlin
15. B. Hammer, B.J. Jain, Neural methods for non-standard data, in: Proceedings of ESANN 2004, D-side, pp. 281-292.
16. IUPAC, Nomenclature of Organic Chemistry, Pergamon Press, Oxford, 1979.
17. T. Jaakkola M. Diekhans D. Haussler A discriminative framework for detecting remote protein homologies J. Comput. Biol. 7 1,2 2000 95-114
18. N. Lavrač S. Džeroski Inductive Logic Programming: Techniques and Applications 1994 Ellis Horwood Chichester
19. A. Micheli, Recursive Processing of Structured Domains in Machine Learning, Ph.D. Thesis, Department of Computer Science, University of Pisa, 2003, TD-13/03.
20. A. Micheli A. Sperduti A. Starita A.M. Bianucci Analysis of the internal representations developed by neural networks for structures applied to quantitative structure-activity relationship studies of benzodiazepines J. Chem. Inf. Comput. Sci. 41 1 2001 202-218
21. A. Micheli, A. Sperduti, A. Starita, A.M. Bianucci, Design of new biologically active molecules by recursive neural networks, in: IJCNN'2001-Proceedings of the INNS-IEEE International Joint Conference on Neural Networks, Washington, DC, July 2001, pp. 2732-2737.
22. A. Micheli, D. Sona, A. Sperduti, Contextual processing of structured data by recursive cascade correlation, IEEE Trans. Neural Networks, Vol. 15, n.6, pp. 1396-1410, 2004.
23. A. Micheli, F. Portera, A. Sperduti, QSAR/QSPR studies by kernel machines, recursive neural networks and their integration, in: B. Apolloni, M. Marinaro, R. Tagliaferri (Eds.), 14th Italian Workshop on Neural Nets, WIRN VIETRI 2003, Lecture Notes in Computer Science, vol. 2859, Springer, Berlin, 2003.
24. A. Micheli, F. Portera, A. Sperduti, A preliminary experimental comparison of recursive neural networks and a tree kernel method for qsar/qspr regression tasks, in: Proceedings of ESANN'2004, D-side, 2004, pp. 293-298.
25. S. Muggleton, Inductive Logic Programming, vol. 38, A.P.I.C. series, Academic Press Ltd., London, 1992.
26. L. Nicotra, A. Micheli, A. Starita, Fisher kernel for tree structured data, in: Proceedings of the IEEE International Joint Conference on Neural Networks, July 2004, pp. 1917-1922.
27. J. Ramon, T. Gartner, Expressivity versus efficiency of graph kernels, in: First International Workshop on Mining Graphs, Trees and Sequences, 2003, http://www.ar.sanken.osaka-u.ac.jp/washio/list/7.pdf.
28. A. Sperduti D. Majidi A. Starita Extended cascade-correlation for syntactic and structural pattern recognition P. Perner P. Wang A. Rosenfeld Advances in Structural and Syntactical Pattern Recognition, Lecture Notes in Computer Science vol. 1121 1996 Springer Berlin 90-99
29. A. Sperduti A. Starita Supervised neural networks for the classification of structures IEEE Trans. Neural Networks 8 3 1997 714-735
30. V.N. Vapnik Statistical Learning Theory 1998 Wiley New York
31. S. Vishwanathan, A.J. Smola, Fast kernels for string and tree matching, in: S. Becker, S. Thrun, K. Obermayer (Eds.), Advances in Neural Information Processing Systems 15, MIT, Cambridge, MA, pp. 569-576, 2003.