Package org.nd4j.linalg.learning

Interface Summary

Interface	Description
GradientUpdater	Gradient modifications: Calculates an update and tracks related information for gradient changes over time for handling updates.
GradientUpdaterAggregator	The GradientUpdaterAggregator is used (typically in distributed learning scenarios) to combine separate GradientUpdater instances for different networks (usually by averaging).

Class Summary

Class	Description
AdaDelta	http://www.matthewzeiler.com/pubs/googleTR2012/googleTR2012.pdf Ada delta updater.
AdaDelta.AdaDeltaAggregator
AdaGrad	Vectorized Learning Rate used per Connection Weight Adapted from: http://xcorr.net/2014/01/23/adagrad-eliminating-learning-rates-in-stochastic-gradient-descent/ See also http://cs231n.github.io/neural-networks-3/#ada
AdaGrad.AdaGradAggregator
Adam	The Adam updater.
Adam.AdamAggregator
Nesterovs	Nesterov's momentum.
Nesterovs.NesterovsAggregator
RmsProp	RMS Prop updates: http://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf http://cs231n.github.io/neural-networks-3/#ada
RmsProp.RmsPropAggregator
Sgd
Sgd.SgdAggregator