| Class | Description |
|---|---|
| AdaGrad<V extends java.lang.Number> |
Adaptive Gradients, or AdaGrad for short, is an extension of the gradient descent optimization
algorithm that adjusts the step size for each parameter based on the squared gradients
seen over the course of previous optimization steps.
|
| AdaGradFactory | |
| ADAM<V extends java.lang.Number> |
ADAM (short for Adaptive Moment Estimation) is an adaptive learning rate optimization algorithm that utilises both
momentum and scaling, combining the benefits of RMSProp and SGD with respect to Momentum.
|
| ADAMFactory | |
| Momentum<V extends java.lang.Number> | |
| MomentumFactory | |
| RMSProp<V extends java.lang.Number> |
Root Mean Squared Propagation, or RMSProp,
is an extension of gradient descent and the AdaGrad version of gradient
descent that uses a decaying average of partial gradients in the adaptation of the
step size for each parameter.
|
| RMSPropFactory | |
| SGD<V> |
Stochastic Gradient Descent is an iterative optimization technique
that uses the gradient of a weight variable to adjust said variable,
in order to reduce the error used to calculate said gradient.
|
| SGDFactory |