Uses of Interface
jsat.math.optimization.stochastic.GradientUpdater

Packages that use GradientUpdater

Package	Description
jsat.classifiers.linear
jsat.classifiers.neuralnetwork
jsat.math.optimization.stochastic

Uses of GradientUpdater in jsat.classifiers.linear

Methods in jsat.classifiers.linear that return GradientUpdater

Modifier and Type	Method and Description
GradientUpdater	LinearSGD.getGradientUpdater()

Methods in jsat.classifiers.linear with parameters of type GradientUpdater

Modifier and Type	Method and Description
void	LinearSGD.setGradientUpdater(GradientUpdater gradientUpdater) Sets the method that will be used to update the weight vectors given their gradient information.

Uses of GradientUpdater in jsat.classifiers.neuralnetwork

Methods in jsat.classifiers.neuralnetwork that return GradientUpdater

Modifier and Type	Method and Description
GradientUpdater	SGDNetworkTrainer.getGradientUpdater()

Methods in jsat.classifiers.neuralnetwork with parameters of type GradientUpdater

Modifier and Type	Method and Description
void	SGDNetworkTrainer.setGradientUpdater(GradientUpdater updater) Sets the gradient update that will be used when updating the weight matrices and bias terms.

Uses of GradientUpdater in jsat.math.optimization.stochastic

Classes in jsat.math.optimization.stochastic that implement GradientUpdater

Modifier and Type	Class and Description
class	AdaDelta AdaDelta is inspired by AdaGrad and was developed for use primarily in neural networks.
class	AdaGrad AdaGrad provides an adaptive learning rate for each individual feature See: Duchi, J., Hazan, E.,&Singer, Y.
class	Adam Adam is inspired by RMSProp and AdaGrad, where the former can be seen as a special case of Adam.
class	NAdaGrad Normalized AdaGrad provides an adaptive learning rate for each individual feature, and is mostly scale invariant to the data distribution.
class	RMSProp rmsprop is an adpative learning weight scheme proposed by Geoffrey Hinton.
class	Rprop The Rprop algorithm provides adaptive learning rates using only first order information.
class	SGDMomentum Performs unaltered Stochastic Gradient Decent updates using either standard or Nestrov momentum.
class	SimpleSGD Performs unaltered Stochastic Gradient Decent updates computing x = x- η grad Because the SimpleSGD requires no internal state, it is not necessary to call SimpleSGD.setup(int).

Methods in jsat.math.optimization.stochastic that return GradientUpdater

Modifier and Type	Method and Description
GradientUpdater	GradientUpdater.clone()