Kalman filter

Ensemble Kalman Filter Optimizing Deep Neural Networks: An Alternative Approach to Non-performing Gradient Descent
The successful training of deep neural networks is dependent on initialization schemes and choice of activation functions. …
Alper Yegenoglu, Kai Krajsek, Sandra Diaz-Pier, Michael Herty
Cite Code DOI
Ensemble Kalman Filter Optimizing Deep Neural Networks: An Alternative Approach to Non-performing Gradient Descent