Release Version 1.17

Models

• 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.

Others

• 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.