Training Optimization of Feedforward Neural Network for Binary Classification

摘要

In this paper, we present a heuristic based technique to reduce the training time of a feedforward neural network by intuiting some of the parameters involved in construction and initialization of the network. These estimated parameters include the number and size of the hidden layers along with the weights related to the neurons. The weights and network architecture is estimated before training by formulating a geometric approximation of the target function we want the network to learn. This specific configuration will allow the network to learn the optimum weights in less iterations than in the case of random initialization of weights.