Efficient learning in Multi-Layered Perceptron using the Grow-And-Learn algorithm
The well-known Multi-Layered Perceptron has gained power thanks to the Back Propagation Algorithm. The difficulty which still subsists is its time-wasting. In fact, the learning process can be improved by using the Grow-And-Learn (GAL) algorithm. In this paper, we present such a hybrid system: the cooperation between GAL and MLP networks. The obtained system is more rapid and more efficient than the classic Back Propagation which computes on the MLP.
Keywordscharacter recognition co-operation neural networks
Unable to display preview. Download preview PDF.
- 1.Y. L. Cun, “Generalization and network design strategies,” technical report crg-tr-89-4, University of Toronto, 1989.Google Scholar
- 2.N. Ohnishi, A. Okamoto, and N. Sugie, “Selective presentation of learning samples for efficient learning in multi-layered perceptron,” Proceedings of the International Joint Conference on Neural Networks, vol. 1, pp. 278–289, Jan. 1990.Google Scholar
- 3.E. Alpaydin, “Grow-And-Learn: an incremental method for category learning,” Proceedings of the International Conference on Neural Networks, pp. 761–764, July 1990.Google Scholar