A quotient gradient method to train artificial neural networks

In this study we introduce a new approach to train a fully recurrent artificial neural network by solving a constraint satisfaction problem using the quotient gradient method. The quotient gradient method is a trajectory based methodology for global optimization that does not suffer from the problem of local minima encountered in Newton based methods. Simulation results show that the network trained with the quotient gradient method perform better than traditional error backpropagation. The method is also easier to implement in comparison to other global optimization techniques such as genetic algorithms.