MUpstart-A constructive neural network learning algorithm for multi-category pattern classification

IEEE International Conference on Neural Networks - Conference Proceedings

Volumn 3, Issue , 1997, Pages 1924-1929

  Parekh, R ^a   Yang, Jihoon ^a   Honavar, V ^a  

^a Iowa State University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION ERRORS; CONSTRUCTIVE LEARNING ALGORITHM; CONSTRUCTIVE NEURAL NETWORK; INPUT PATTERNS; MULTIPLE OUTPUTS; REAL-VALUED PATTERNS; REAL-WORLD DATASETS;

LEARNING ALGORITHMS; NEURAL NETWORKS; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; ITERATIVE METHODS; PATTERN RECOGNITION;

CLASSIFICATION (OF INFORMATION); NEURAL NETWORKS;

ZERO CLASSIFICATION ERRORS;

EID: 0030688750     PISSN: 10987576     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICNN.1997.614193     Document Type: Conference Paper

References (13)

1. N. Burgess. A constructive algorithm that converges for real-valued input patterns. International Journal of Neural Systems, 5(l):59-66,1994.
2. C.-H. Chen, R. Parekh, J. Yang, K. Balakrishnan, and V. Honavar. Analysis of decision boundaries generated by constructive neural network learning algorithms. In Proceedings of WCNN'95, July 17-21, Washington D.C., volume 1,pages 628-635,1995.
3. M. Frean. The upstart algorithm: A method for constructing and training feedforward neural networks. Neural Computation, 2:198-209,1990.
4. M. Frean. A thermal perceptron learning rule. Neural Computation, 4:946-957,1992.
5. S. Gallant. Perceptron based learning algorithms. IEEE Transactions on Neural Networks, 1(2):179-191, June 1990.
6. S. Gallant. Neural Network Learning and Expert Systems. MIT Press, Cambridge, MA, 1993.
7. M. Mdzard and J. Nadal. Learning feed-forward networks: The tiling algorithm. J. Phys. A: Math. Gen., 22:2191-2203, 1989.
8. R. G. Parekh, J. Yang, and V. G. Honavar. Constructive neural network learning algorithms for multi-category classification. Technical Report ISU-CS-TR95-15a, Department of Computer Science, Iowa State University, 1995.
9. R. G. Parekh, J. Yang, and V. G. Honavar. Constructive neural network learning algorithms for multi-category real-valued pattern classification. Technical Report ISU-CS-TR97-06, Department of Computer Science, Iowa State University, 1997.
10. H. Poulard. Barycentric correction procedure: A fast method of learning threshold units. In Proceedings of WCNN'95, July 17-21, Washington D.C., volume 1, pages 710-713,1995.
11. F. Rosenblatt. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65:386-408,1958.
12. J. Saffery and C. Thornton. Using stereographic projection as a preprocessing technique for upstart. In Proceedings of the International Joint Conference on Neural Networks, pages II441-446. IEEE Press, July 1991.
13. J. Yang, R. G. Parekh, and V. G. Honavar. Empirical comparison of graceful variants of the perceptron learning algorithm on non-separable data sets. In preparation, 1997.