Package deepnetts.net.train.opt
package deepnetts.net.train.opt
Optimization methods used by training algorithm.
-
ClassDescriptionSkeletal implementation of the Optimizer interface to minimize effort to implement specific optimizers.Implementation of ADADELTA which is a modification of AdaGrad that uses only a limited window of previous gradients.Implementation of ADAGRAD
Optimizer, which uses sum of squared previous gradients to adjust a global learning rate for each weight.Implementation of Adam optimizer which uses an estimation of a gradient statistic (mean and variance) to adjust learning rate for each weight.https://www.coursera.org/learn/deep-neural-network/lecture/hjgIA/learning-rate-decayMomentum optimization adds momentum parameter to basic Stochastic Gradient Descent, which can accelerate the process.Optimization technique to tune network's weights parameters used by training algorithm.Supported types of optimization methods used by back-propagation training algorithm.A variation of AdaDelta optimizer.Basic Stochastic Gradient Descent optimization algorithm, which iteratively changes weights in order to find minimum of loss function.