Statements (22)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:mathematical_optimization
|
| gptkbp:advantage |
handles non-stationary objectives
reduces oscillations in parameter updates |
| gptkbp:category |
gradient descent optimization
|
| gptkbp:commonIn |
training neural networks
|
| gptkbp:hyperparameter |
learning rate
decay rate epsilon |
| gptkbp:implementedIn |
available in Keras
available in PyTorch available in TensorFlow |
| gptkbp:proposedBy |
gptkb:Geoffrey_Hinton
2012 |
| gptkbp:purpose |
adaptive learning rate optimization
|
| gptkbp:relatedTo |
gptkb:Adam
gptkb:AdaGrad |
| gptkbp:updateRule |
divides learning rate by moving average of squared gradients
|
| gptkbp:usedIn |
gptkb:machine_learning
deep learning |
| gptkbp:bfsParent |
gptkb:machine_learning
|
| gptkbp:bfsLayer |
4
|
| https://www.w3.org/2000/01/rdf-schema#label |
RMSprop
|