[Master Index] [Index for export/lyngby]

lyngby_nn_qddeus

(export/lyngby/lyngby_nn_qddeus.m)


Function Synopsis

ddEUU = lyngby_nn_qddeus(X, V, W, H, H12)

Help text

 lyngby_nn_qddeus     - 2nd der., quad., all weights, gauss approx.

       function ddEUU = lyngby_nn_qddeus(X, V, W, H, H12)

	Input:  X       Neural network input
               V       Input weights
               W       Output weights
               H12     (1-tanh(XV).^2) 

       Output: ddEUU   Derivative as a Hessian matrix

       Gauss-Newton (symmetric) approximation to the second order
       derivative of the qaudratic error function with respect to
       both the input and the output weights in the neural network.

Cross-Reference Information

This function calls
This function is called by

Produced by mat2html on Wed Jul 29 15:43:40 2009
Cross-Directory links are: OFF