NeuralNet::Optimizer Class Reference

Inheritance diagram for NeuralNet::Optimizer:

Public Member Functions
	Optimizer (double alpha)
virtual void	updateWeights (Eigen::MatrixXd &weights, const Eigen::MatrixXd &weightsGrad)=0
	This function updates the weights passed based on the selected Optimizer and the weights gradients.
virtual void	updateBiases (Eigen::MatrixXd &biases, const Eigen::MatrixXd &biasesGrad)=0
	This function updates the biases passed based based on the Optimizer and the biases gradients.

Protected Member Functions
virtual void	insiderInit (size_t size)=0
	This function's purpose is to provide an interface to perform updates for the Optimizers from within the network.

Protected Attributes
double	alpha

Friends
class	Network

Member Function Documentation

insiderInit()

virtual void NeuralNet::Optimizer::insiderInit ( size_t size )

protectedpure virtual

This function's purpose is to provide an interface to perform updates for the Optimizers from within the network.

Parameters

size	The size (for now it's only used to init the layer's in the Adam optimizer)

This function returns nothing

updateBiases()

virtual void NeuralNet::Optimizer::updateBiases ( Eigen::MatrixXd & biases, const Eigen::MatrixXd & biasesGrad )

pure virtual

This function updates the biases passed based based on the Optimizer and the biases gradients.

Parameters

biases	The biases that should be updated
biasesGrad	The biases gradient

The function will return void, since it only performs an update on the biases passed

Implemented in NeuralNet::Adam, and NeuralNet::SGD.

updateWeights()

virtual void NeuralNet::Optimizer::updateWeights ( Eigen::MatrixXd & weights, const Eigen::MatrixXd & weightsGrad )

pure virtual

This function updates the weights passed based on the selected Optimizer and the weights gradients.

Parameters

weights	The weights that should be updated
weightsGrad	The weights gradient

The function will return void, since it only performs an update on the weights passed

Implemented in NeuralNet::Adam, and NeuralNet::SGD.

---

The documentation for this class was generated from the following file:

• /github/workspace/src/NeuralNet/optimizers/Optimizer.hpp