Abstract
In this paper a new neural network structure, called Syntactical Self-Organizing Map (SSOM), is introduced. SSOM is obtained from classical (numerical) Kohonen neural network and is specifically for classifying the syntactical structures, like: strings, trees or graphs. After defining the SSOM structure and algorithm, in the third part of the paper an application of character recognition is solved using SSOM. To point out the performances of the new neural network, a comparison of results obtained using the SSOM and the Fu and Lu's clustering algorithm [10] for the same application is done. Moreover, we show that the syntactical Kohonen map have also the topological feature like the numerical one.
Preview
Unable to display preview. Download preview PDF.
References
H. C. Andrews: Introduction to Mathematical Techniques in Pattern Recognition, Wiley, New York, 1972.
N. M. Cheung, A. B. Horner: “Group Synthesis with Genetic Algorithm”, Journal of the Audio Engineering Society, vol. 44, no. 3, March 1996, pp. 130–147.
E. Diday, J. C. Simon: “Clustering Analysis”, Digital Pattern Recognition, K. S. Fu Ed. Springer-Verlag, New York, 1976.
R. O. Duda, P. E. Hart: Pattern Classification and Scene Analysis, Wiley, New York, 1972.
J. Fehlauer, B. A. Eisenstein: “Structural Editing by a Point Density Function”, IEEE Trans. Syst., Man, Cybern., vol. SMC-8, no. 5, May 1978, pp. 362–370.
H. Freeman: “On the Encoding of Arbitrary Geometric Configuration”, IEEE Trans. Electon. Comput., vol. EC-10, 1961, pp. 260–268.
G. P. Geaves: “Design and Validation of a System For Selecting Optimized Midrange Loudspeaker Diaphragm Profiles”, Journal of the Audio Engineering Society, vol. 44, no. 3, March 1996, pp. 107–119.
T. Kohonen: “Adaptive, Associative and Self-Organizing Function in Neural Computing”, in Artificial Neural Networks, pp. 42–51, IEEE Press, Piscataway, NJ, 1992
T. Kohonen: “The “Neural” Phonetic Typewriter”, in Artificial Neural Networks, pp. 409–421, IEEE Press, Piscataway, NJ, 1992
S. Y. Lu, K. S. Fu: “A Sentence-to-Sentence Clustering Procedure for Pattern Analysis”, IEEE Trans. Syst., Man, Cybern., vol. SMC-8, no. 5, May 1978, pp. 381–389.
S. Y. Lu: “A Tree-to-Tree Distance and Its Application to Cluster Analysis”, IEEE Trans. Patterns Anal. Machine Intell., vol. PAMI-1, no. 2, April 1979, pp. 219–227.
S. Y. Lu, K. S. Fu: “Error-Correcting Tree Automata for Syntactic Pattern Recognition and Image Processing”, RPI, Troi, NY., June 6–8 1977.
V. Neagoe, O. Stanasila: Teoria Recunoasterii Formelor, Ed. Academiei Romane Academiei Romane, Bucuresti, 1992
P. K. Simpson: “Foundation of Neural Networks”, in Artificial Neural Networks, pp. 3–24, IEEE Press, Piscataway, NJ, 1992
A. C. Show: “A Formal Picture Description Scheme as a Basis for Picture Processing Systems”, Inform. Contr., vol. 14, 1969.
R. A. Wagner, M. J. Fisher: “The String to String Correction Problem”, J. Ass. Comput. Mach., vol. 21, Jan. 1974.
Z. Wu, R. Leahly: “An Optimal Graph Theoretic Approach to Data Clustering: Theory and Its Application to Image Segmentation”, vol. 15, no. 11, Nov. 1993, pp. 1101–1113.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Grigore, O. (1997). Syntactical Self-Organizing Map. In: Reusch, B. (eds) Computational Intelligence Theory and Applications. Fuzzy Days 1997. Lecture Notes in Computer Science, vol 1226. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62868-1_103
Download citation
DOI: https://doi.org/10.1007/3-540-62868-1_103
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62868-2
Online ISBN: 978-3-540-69031-3
eBook Packages: Springer Book Archive