Optimizers¶
Zeiler’s ADADELTA. |
|
AdaGrad optimizer. |
|
Adam optimizer. |
|
Momentum SGD optimizer. |
|
Momentum SGD optimizer. |
|
Nesterov’s Accelerated Gradient. |
|
RMSprop optimizer. |
|
Alex Graves’s RMSprop. |
|
Vanilla Stochastic Gradient Descent. |
|
Simon Funk’s SMORMS3. |
Optimizer base classes¶
Base class of all numerical optimizers. |
|
Base class of all update rules. |
|
Set of hyperparameter entries of an optimizer. |
|
Base class of all single gradient-based optimizers. |
Hook functions¶
Optimizer/UpdateRule hook function for weight decay regularization. |
|
Optimizer/UpdateRule hook function for Lasso regularization. |
|
Optimizer hook function for gradient clipping. |
|
Optimizer/UpdateRule hook function for gradient clipping. |
|
Optimizer/UpdateRule hook function for adding gradient noise. |
|
Optimizer/UpdateRule hook function for layer wise adaptive rate scaling. |