Hessian with Mini-Batches for Electrical Demand Prediction
Israel Elias, José de Jesús Rubio, David Ricardo Cruz, Genaro Ochoa, Juan Francisco Novoa, Dany Ivan Martinez, Samantha Muñiz, Ricardo Balcázar, Enrique García, Cesar Felipe Juárez
Abstract
The steepest descent method is frequently used for neural network tuning. Mini-batches are commonly used to get better tuning of the steepest descent in the neural network. Nevertheless, steepest descent with mini-batches could be delayed in reaching a minimum. The Hessian could be quicker than the steepest descent in reaching a minimum, and it is easier to achieve this goal by using the Hessian with mini-batches. In this article, the Hessian is combined with mini-batches for neural network tuning. The discussed algorithm is applied for electrical demand prediction.