TY  - GEN 
AU  - García Cabello, Julia
PY  - 2023
UR  - https://hdl.handle.net/10481/86197
AB  - For Deep Neural Networks (DNN), the standard gradient-based algorithms may not be efficient because of the raised computational expense resulting from the increase in the number of layers. This paper offers an alternative to the classic training...
LA  - eng
PB  - Elsevier
KW  - Separable function
KW  - Principle of optimality
KW  - Composition of parametric functions
KW  - Universal approximators of continuous functions
TI  - Improved Deep Neural Network Performance under Dynamic Programming mode
DO  - 10.1016/j.neucom.2023.126785
ER  -