|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
public interface ComputeHessian
Compute (estimate) the Hessian matrix. The Hessian matrix is a matrix of the second derivatives of the neural network. This is a square matrix with rows and columns equal to the number of weights in the neural network. A Hessian matrix is useful for several neural network functions. It is also used by the Levenberg Marquardt training method. http://en.wikipedia.org/wiki/Hessian_matrix
Method Summary | |
---|---|
void |
clear()
Clear the Hessian and gradients. |
void |
compute()
Compute the Hessian. |
double[] |
getGradients()
The gradeints. |
double[][] |
getHessian()
|
Matrix |
getHessianMatrix()
|
double |
getSSE()
|
void |
init(BasicNetwork theNetwork,
MLDataSet theTraining)
Init the class. |
Method Detail |
---|
void init(BasicNetwork theNetwork, MLDataSet theTraining)
theNetwork
- The neural network to train.theTraining
- The training set to train with.void compute()
double[] getGradients()
double getSSE()
void clear()
Matrix getHessianMatrix()
double[][] getHessian()
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |