SuperNN
1.0.0
|
Modified improved resilient backpropagation algorithm. More...
Public Member Functions | |
IRpropL1 () | |
virtual | ~IRpropL1 () |
double | delta (Network &net, unsigned l, unsigned n) |
Calculates the local error gradient for each neuron. More... | |
![]() | |
IRprop () | |
virtual | ~IRprop () |
virtual void | prepare (Network &net) |
Prepares the trainer and a neural network for training. More... | |
virtual unsigned | train (Network &net, const Data &data, double dmse=0, unsigned max_epochs=1000) |
Adjusts the synaptic weight of an artificial neural network in order to minimize the error (MSE for standard l2 training or MAE for specific l1 training). More... | |
![]() | |
virtual | ~TrainingAlgorithm () |
virtual void | clear_derror_acc (Network &net) |
Clears the accumulated error partial derivatives. More... | |
virtual void | derror_acc (Network &net) |
Accumulates the error partial derivative in respect to the weights, for each connection of the neural network. More... | |
Additional Inherited Members | |
![]() | |
double | delta_df |
Weight change decrease factor. More... | |
double | delta_if |
Weight change increase factor. More... | |
double | delta_max |
Maximum weight change. More... | |
double | delta_min |
Minimum weight change. More... | |
double | delta_zero |
Initial weight change. More... | |
![]() | |
virtual void | update_weights (Network &net) |
Updates the weights, using the partial error derivative sign change as guide. More... | |
![]() | |
virtual void | check (const Network &net, const Data &data) const |
Checks if the dimensions match and if the training algorithm can be used with a given network and data. More... | |
Modified improved resilient backpropagation algorithm.
Minimizes the absolute error instead of the squared error.
Definition at line 220 of file training.hpp.
SuperNN::IRpropL1::IRpropL1 | ( | ) |
Definition at line 344 of file training.cpp.
|
virtual |
Definition at line 348 of file training.cpp.
|
virtual |
Calculates the local error gradient for each neuron.
It's a recursive operation, where calculating the delta for a neuron will automatically calculate the delta for the neurons in the next layers that have connections with this neuron.
For an output neuron j:
For a hidden neuron j:
net | Neural network to be used |
l | Layer where the neuron is located |
n | Neuron position in the layer |
Reimplemented from SuperNN::TrainingAlgorithm.
Definition at line 352 of file training.cpp.