research
∙
02/28/2018
Avoiding overfitting of multilayer perceptrons by training derivatives
Resistance to overfitting is observed for neural networks trained with e...
research
∙
12/14/2017
Neural networks catching up with finite differences in solving partial differential equations in higher dimensions
Fully connected multilayer perceptrons are used for obtaining numerical ...
research
∙
12/12/2017
Enhancing approximation abilities of neural networks by training derivatives
Method for increasing precision of feedforward networks is presented. Wi...
research
∙
12/12/2017