Package org.ea.javacnn.trainers

Class Summary

Class	Description
AdaDeltaTrainer	Adaptive delta will look at the differences between the expected result and the current result to train the network.
AdaGradTrainer	The adaptive gradient trainer will over time sum up the square of the gradient and use it to change the weights.
AdamTrainer	Adaptive Moment Estimation is an update to RMSProp optimizer.
NesterovTrainer	Another extension of gradient descent is due to Yurii Nesterov from 1983,[7] and has been subsequently generalized
SGDTrainer	Stochastic gradient descent (often shortened in SGD), also known as incremental gradient descent, is a stochastic approximation of the gradient descent optimization method for minimizing an objective function that is written as a sum of differentiable functions.
Trainer	Trainers take the generated output of activations and gradients in order to modify the weights in the network to make a better prediction the next time the network runs with a data block.
WindowGradTrainer	This is AdaGrad but with a moving window weighted average so the gradient is not accumulated over the entire history of the run.