Improved calculations related to calculation of cost function derivatives involving both regularization and optimizers.
LongShortTermMemory and RecurrentNeuralNetwork models are removed as these do not work well with the current API.
Made some bug fixing.
Refactored RandomNetworkDistillation so that it no longer inherits NeuralNetwork. Please use setModel() function to add neural network model to it. Also added deep copy option for TargetModelParameters and PredictorModelParameters.
Regularization no longer need number of data, instead the gradient method models will handle the operations related to it instead.