Elias, Israel;
Rubio, José de Jesús;
Cruz, David Ricardo;
Ochoa, Genaro;
Novoa, Juan Francisco;
Martinez, Dany Ivan;
Muñiz, Samantha;
Balcazar, Ricardo;
Garcia, Enrique;
Juarez, Cesar Felipe
Hessian with Mini-Batches for Electrical Demand Prediction
Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
Hessian with Mini-Batches for Electrical Demand Prediction
Beteiligte:
Elias, Israel;
Rubio, José de Jesús;
Cruz, David Ricardo;
Ochoa, Genaro;
Novoa, Juan Francisco;
Martinez, Dany Ivan;
Muñiz, Samantha;
Balcazar, Ricardo;
Garcia, Enrique;
Juarez, Cesar Felipe
Erschienen:
MDPI AG, 2020
Erschienen in:
Applied Sciences, 10 (2020) 6, Seite 2036
Beschreibung:
<jats:p>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.</jats:p>