Data-Driven Learning of Feedforward Neural Networks with Different Activation Functions

This work contributes to the development of a new data-driven method (D-DM) feedforward neural networks (FNNs) learning. was proposed recently as way improving randomized learning FNNs by adjusting network parameters target function fluctuations. The employs logistic sigmoid activation functions for hidden nodes. In this study, we introduce other functions, such bipolar sigmoid, sine function, saturating linear reLU, and softplus. We derive formulas their parameters, i.e. weights biases. simulation evaluate performance FNN with different functions. results indicate that perform much better than others in approximation complex, fluctuated