Geometrical initialization, parametrization and control of multilayer perceptrons: application to function approximation

F. Rossi, C. Gegout
1994 Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)  
This paper proposes a new method to reduce training time for neural nets used as function approximators. This method relies on a geometrical control of Multilayer Perceptrons (MLP). A geometrical initialization gives first better starting points for the learning process. A geometrical parametrization achieves then a more stable convergence. During the learning process, a dynamic geometrical control helps to avoid local minima. Finally, simulation results are presented, showing drastic reduction
more » ... g drastic reduction in training time and increase in convergence rate.
doi:10.1109/icnn.1994.374223 fatcat:54u6plfhebdancr2kbtlq3h3em