Creates a new optimizer object. If there are no parameters given for that particular argument, then that argument will use default value.
NesterovAcceleratedAdaptiveMomentEstimation.new(beta1: number, beta2: number, epsilon: number): OptimizerObject
beta1: The decay rate of the moving average of the first moment of the gradients.
beta2: The decay rate of the moving average of the squared gradients.
epsilon: The value to ensure that the numbers are not divided by zero.
NesterovAcceleratedAdaptiveMomentEstimation:setBeta1(beta1: number)
NesterovAcceleratedAdaptiveMomentEstimation:setBeta2(beta2: number)
NesterovAcceleratedAdaptiveMomentEstimation:setEpsilon(epsilon: number)
Reset optimizer’s stored values (excluding the parameters).
NesterovAcceleratedAdaptiveMomentEstimation:reset()