Implements the following algorithm: "Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights" by Derrick Nguyen and Bernard Widrow. More...
#include <Weights_Initializer.h>
Public Member Functions | |
Weights_Initializer (int rnd_seed=-1) | |
Constructor, takes internal random numbers generator seed value as a parameter. If no seed is specified _time32(NULL) function result is taken as a seed. | |
void | Set_Weights_Count (int count) |
Sets the number of weights to calculate. | |
void | Set_Hidden_Neurons_Count (int count) |
Sets the number of neurons in hidden layer. | |
void | Get_Weights (std::vector< double > &output, int weights_count=0, int hidden_neurons_count=0) |
Calculates initial weights based on weights_count and hidden_neurons_count. | |
double | Get_Bias_Weight () |
Calculates random bias weight based on weights_count and hidden_neurons_count. | |
bool | Validate (const std::vector< double > &input, double precision=0.0001) |
Validates Get_Weights() result with the specified precision. |
Implements the following algorithm: "Improving the Learning Speed of 2-Layer Neural Networks by Choosing Initial Values of the Adaptive Weights" by Derrick Nguyen and Bernard Widrow.