Staged training of Neocognitron by evolutionary algorithms

Proceedings of the 1999 Congress on Evolutionary Computation, CEC 1999

Volumn 3, Issue , 1999, Pages 1965-1972

  Pan, Zhengjun ^a,b   Sabisch, Theo ^a   Adams, Rod ^a   Bolouri, Hamid ^a  

^a UNIVERSITY OF HERTFORDSHIRE   (United Kingdom)

^b WUHAN UNIVERSITY   (China)

Author keywords

evolutionary computation; learning; medical image; Neocognitron; neural network; Pattern recognition

Indexed keywords

CALCULATIONS; COMPLEX NETWORKS; IMAGE RECOGNITION; MAMMALS; MEDICAL IMAGING; NEURAL NETWORKS; PATTERN RECOGNITION;

COMPLEX NEURAL NETWORKS; GRADIENT-DECENT ALGORITHM; LEARNING; MAMMALIAN VISUAL SYSTEMS; NEOCOGNITRON; REAL-WORLD PROBLEM;

EVOLUTIONARY ALGORITHMS;

EID: 20444408205     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/CEC.1999.785515     Document Type: Conference Paper

References (17)

1. Abutaleb, A., Delalic, Z. J., Ech, R., and Siegel, J. A. (1989). Automated analysis for scintigraphic evaluation of gastric emptying using invariant moments. IEEE Transactions on Medical Imaging, 8(4):364-369.
2. Chin, R. T. and Dyer, C. R. (1986). Model-based recognition in robot vision. Computing Surveys, 18:68-108.
3. Fukushima, K. (1988). Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Networks, 1:119-30.
4. Fukushima, K. and Miyake, S. (1982). Neocognitron: a new algorithm for pattern recognition tolerant of deformations and shifts in position. Pattern Recognition, 15(6):455-469.
5. Fukushima, K. and Wake, N. (1991). Handwritten alphanumeric character recognition by the neocognitron. IEEE Transactions on Neural Networks, 2(3):355-65.
6. Hinton, G. E. (1987). Learning translation invariant recognition in a massively parallel network. In Proceedings of Parallel Architectures and Languages Europe (PARLE), pages 1-13.
7. Le Cun, Y. and Farber, R. (1989). Backpropagation applied to handwritten zip code recognition. Neural Computation, 1(4):541-551.
8. Lovell, D. R. (1994). The Neocognitron as a system for handwritten character recognition: limitations and improvements. PhD dissertation, University of Queensland.
9. Lovell, D. R., Downs, T., and Tsoi, A. C. (1997). An evaluation of the neocognitron. IEEE Transactions on Neural Networks, 8(5):1090-105.
10. Pan, Z. and Kang, L. (1997). An adaptive evolutionary algorithms for numerical optimization. In Yao, X., Kim, J. H., and Furuhashi, T., editors, Simulated Evolution and Learning, number 1285 in Lecture Notes in Computer Science, pages 27-34, Heidelberg. Springer-Verlag.
11. Pan, Z., Kang, L., and Chen, Y. (1998). Evolutionary Computation. Tsinghua University Press, Beijing (In Chinese).
12. Sabisch, T. (1998). Towards automatic registration of magnetic resonance images of the brain using neural networks. PhD dissertation, University of Hertfordshire, UK.
13. Sabisch, T., Ferguson, A., and Bolouri, H. (1997). Rotation, translation and scaling tolerant recognition of complex shapes using a hierarchical self-organising neural network. In Proceedings of international conference on neural information processing (ICONIP'97), volume 2, pages 1174-1178, Dunedin, New Zealand. Springer.
14. Sabisch, T., Ferguson, A., and Bolouri, H. (1998). Identification of complex shapes using a self-organising neural system. IEEE Transactions on Neural Networks, submitted Oct. 1998, (TNN-A245).
15. Shridhar, M. and Badreldin, A. (1984). High accuracy character recognition algorithm using fourier and topological descriptors. Pattern Recognition, 17(5):515-524.
16. Sung, C. and Wilson, D. (1990). Percognitron: neocognitron coupled with perceptron. In International Joint Conference on Artifical Neural Networks, pages 753-758, Ann Arbor, USA. IEEE.
17. Teo, M. Y., Khoo, L. P., and Sim, S. K. (1997). Application of genetic algorithms to optimise neoconitron network parameters. Neural Network World, 7(3):293-304.