|
| 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.
|
|
|
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.
|
|
◆ 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: