A New Learning Algorithm Using Simultaneous Perturbation with Weight Initialization

摘要

A new learning algorithm is proposed for training single hidden layer feedforward neural network. In each epoch, the connection weights are updated by simultaneous perturbation. Tunneling using perturbation technique is applied to detrap the local minima. The proposed technique is shown to give better convergence results for the selected problems, namely neuro-controller, XOR, L-T character recognition, two spirals, simple interaction function, harmonic function and complicated interaction function.