Performance evaluation of a novel Conjugate Gradient Method for training feed forward neural network
In this paper, we construct a new conjugate gradient method for solving unconstrained optimization problems. The proposed method satisfies the sufficient decent property irrespective of the line search and the global convergence was established under some suitable. Further, the new method was used to train different sets of data via a feed forward neural network. Results obtained show that the proposed algorithm significantly reduces the computational time by speeding up the directional minimization with a faster convergence rate.