Authors : M. Ramakrishnan , K. Ekamavannan , P. Thangavelu and P. Vivekanandan
Abstract: Neural networks have been successfully applied to various pattern recognition and function approximation problems. The author recently introduced left sigmoidal signals and right sigmoidal signals to prove certain function approximation theorems for feed forward neural networks. In this study, by imposing certain conditions on the continuous functions on R, we find those conditions that can be approximated by feed forward neural networks with fixed weights using left sigmoidal signals and right sigmoidal signals.
M. Ramakrishnan , K. Ekamavannan , P. Thangavelu and P. Vivekanandan , 2006. Function Approximation by Feed Forward Neural Networks with a Fixed Weights Using Sigmoidal Signals. Journal of Engineering and Applied Sciences, 1: 293-297.