Representational Capacity of Deep Neural Networks - A Computing Study

Bernhard Bermeitinger
Bernhard Bermeitinger
Tomas Hrycej
Tomas Hrycej

KDIR, pp. 532-538, 2019.

Cited by: 0|Bibtex|Views3|Links
EI

Abstract:

There is some theoretical evidence that deep neural networks with multiple hidden layers have a potential for more efficient representation of multidimensional mappings than shallow networks with a single hidden layer. The question is whether it is possible to exploit this theoretical advantage for finding such representations with help...More

Code:

Data:

Your rating :
0

 

Tags
Comments