Training Recurrent Neural Networks as a Constraint Satisfaction Problem

03/20/2018

∙

by   Hamid Khodabandehlou, et al.

∙

0

∙

share

This paper presents a new approach for training artificial neural networks using techniques for solving the constraint satisfaction problem (CSP). The quotient gradient system (QGS) is a trajectory based method for solving the CSP. This study converts the training set of a neural network into a CSP and uses the QGS to find its solutions. The QGS finds the global minimum of the optimization problem by tracking trajectories of a nonlinear dynamical system and does not stop at a local minimum of the optimization problem. Lyapunov theory is used to prove the asymptotic stability of the solutions with and without the presence of measurement errors. Numerical examples illustrate the effectiveness of the proposed methodology and compare it to a genetic algorithm and error backpropagation