Uses of Interface
deepnetts.net.train.opt.Optimizer

Packages that use Optimizer

Package	Description
deepnetts.net.layers	Neural network layers, which are main building blocks of a neural network.
deepnetts.net.train.opt	Optimization methods used by training algorithm.

Uses of Optimizer in deepnetts.net.layers

Fields in deepnetts.net.layers declared as Optimizer

Modifier and Type	Field	Description
protected Optimizer	AbstractLayer.optimizer

Methods in deepnetts.net.layers that return Optimizer

Modifier and Type	Method	Description
Optimizer	AbstractLayer.getOptimizer()

Uses of Optimizer in deepnetts.net.train.opt

Classes in deepnetts.net.train.opt that implement Optimizer

Modifier and Type	Class	Description
final class	AdaDeltaOptimizer	Implementation of ADADELTA which is a modification of AdaGrad that uses only a limited window of previous gradients.
final class	AdaGradOptimizer	Implementation of ADAGRAD Optimizer , which uses sum of squared previous gradients to adjust a global learning rate for each weight.
final class	AdamOptimizer	Implementation of Adam optimizer which uses an estimation of a gradient statistic (mean and variance) to adjust learning rate for each weight.
final class	MomentumOptimizer	Momentum optimization adds momentum parameter to basic Stochastic Gradient Descent, which can accelerate the process.
final class	RmsPropOptimizer	A variation of AdaDelta optimizer.
final class	SgdOptimizer	Basic Stochastic Gradient Descent optimization algorithm, which iteratively changes weights in order to find minimum of loss function.

Methods in deepnetts.net.train.opt that return Optimizer

Modifier and Type	Method	Description
static Optimizer	Optimizer.create(OptimizerType type, AbstractLayer layer)	Factory method to create different types of optimizers