Fast Pattern Classification with the Multi-layer Cellular Nonlinear Networks (CNN)

다층 셀룰라 비선형 회로망(CNN)을 이용한 고속 패턴 분류

  • 오태완 (전북대 공대 제어계측공학과) ;
  • 이혜정 (전북대 공대 제어계측공학과) ;
  • 손홍락 (전북대 공대 전기정보공학부) ;
  • 김형석 (전북대 공대 전기정보공학부)
  • Published : 2003.09.01

Abstract

A fast pattern classification algorithm with Cellular Nonlinear Network-based dynamic programming is proposed. The Cellular Nonlinear Networks is an analog parallel processing architecture and the dynamic programing is an efficient computation algorithm for optimization problem. Combining merits of these two technologies, fast pattern classification with optimization is formed. On such CNN-based dynamic programming, if exemplars and test patterns are presented as the goals and the start positions, respectively, the optimal paths from test patterns to their closest exemplars are found. Such paths are utilized as aggregating keys for the classification. The algorithm is similar to the conventional neural network-based method in the use of the exemplar patterns but quite different in the use of the most likely path finding of the dynamic programming. The pattern classification is performed well regardless of degree of the nonlinearity in class borders.

Keywords

References

  1. P. K. Patra, M. Nayak, S. K. Nayak, N. K. Gobbak, 'Probabilistic Neural Network for Pattern Classification', Neural Networks, 2002. IJCNN'02 Proceedings of the 2002 International Joint Conf. on, vol.2, pp.1200-1205, 2002 https://doi.org/10.1109/IJCNN.2002.1007665
  2. L. L. Ling, H. M. Cavalcanti, 'Fast and efficient feature extraction based on Bayesian decision boundaries', Pattern Recognition, 2000. Proceedings. 15th International Conf. on, vol. 2, pp. 390-393, 2000 https://doi.org/10.1109/ICPR.2000.906094
  3. T. Horiuchi, 'Decision rule for pattern classification by integrating interval feature values', Pattern Analysis and Machine Intelligence, IEEE Trans. on, vol. 20, pp.440-448, Apr. 1998 https://doi.org/10.1109/34.677286
  4. H.M. Lee, C.M. Chen, J.M. Chen, Y.L. Jou, 'An efficient fuzzy classifier with feature selection based on fuzzy entropy', Systems, Man and Cybernetics, Part B, IEEE Trans. on, vol. 31, pp. 426-432, Jun. 2001 https://doi.org/10.1109/3477.931536
  5. H. Ishibuchi, T. Nakashima, T. Murata, 'Performance evaluation of fuzzy classifier systems for multidimensional pattern classification problems', Systems, Man and Cybernetics, Part B, IEEE Trans. on, vol.29, pp. 601-618, Oct. 1999 https://doi.org/10.1109/3477.790443
  6. X. Chen, D. Jin, Z. Li, 'Fuzzy petri nets for rule-based pattern classification', Communications, Circuits and Systems and West Sino Expositions, IEEE 2002 International Conf. on, vol. 2, pp. 1218-1222, 2002 https://doi.org/10.1109/ICCCAS.2002.1179002
  7. J. W. Go, G. H. Han, H. B. Kim, C. H. Lee, 'Multigradient: A New Neural Network Learning Algorithm for Pattern Classification', Geoscience and Remote Sensing, IEEE Trans. on, vol. 39, pp. 986-993, May, 2001 https://doi.org/10.1109/36.921416
  8. Y. L. Murphe, Y. Luo, 'Feature Extraction for a Multiple Pattern Classification Neural Network System', Pattern Recognition, 2002. Proceedings. 16th International Conf. on, vol.2, pp. 220-223, 2002 https://doi.org/10.1109/ICPR.2002.1048278
  9. L. O. Chua, L. Yang, 'Cellular Neural Networks: theory', IEEE Trans. on Circuits Systems, vol. 35, pp. 1273-1290, 1988 https://doi.org/10.1109/31.7600
  10. L. O. Chua, L. Yang, 'Cellular Neural Networks: applications', IEEE Trans. on Circuits Systems, vol. 35, pp. 1273-1290, 1988 https://doi.org/10.1109/31.7601
  11. T. Roska, L. O. Chua, 'The CNN universal machine: an analogic array computer', IEEE Trans. on Circuits Systems II, vol. CAS-40, pp. 163-173, 1993 https://doi.org/10.1109/82.222815
  12. S. Espejo, R. Dominguez-Castro, G. Linan, A. Rodriguez-Vazquez, 'A $64{\times}64$ CNN universal chip with analog and digital I/O', Electronics, Circuits and Systems, 1998 IEEE International Conf. on, vol. 1, pp. 203-206, 1998 https://doi.org/10.1109/ICECS.1998.813304
  13. R. Bellman, 'Dynamic Programming', Princeton, NJ: Princeton Univ. Press, 1957
  14. H. Kim, H. Son, T. Roska, L. O. Chua, 'Optimal path finding with space- and time-variant metric weights with Multi-layer CNN', International Journal of Circuit Theory and Applications, vol. 30, pp. 247-270, Feb. 2002 https://doi.org/10.1002/cta.199
  15. Analogical and Neural Computing Lab, 'SimCNN-Multi-layer CNN Simulator for Visual Mouse Platform: Reference Manual version 2.2', Computer and Automation Institute(MTA SzTAKI) of the Hungarian Academy of Science, 1998