Hessian with Mini-Batches for Electrical Demand Prediction
Keyword(s):
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.
Keyword(s):
1994 ◽
Vol 05
(04)
◽
pp. 299-312
2016 ◽
Vol 18
(2)
◽
pp. 111-121
◽
Keyword(s):
2018 ◽
Vol 29
(1)
◽
pp. 68-76
◽
2010 ◽
Vol 32
(10)
◽
pp. 2536-2540
◽
2018 ◽
Vol 330
◽
pp. 488-498
Keyword(s):
Keyword(s):
Keyword(s):