[Master Index] [Index for export/lyngby]



Function Synopsis

ddEV = lyngby_nn_eddevds(X, Y, V, W, H12)

Help text

 lyngby_nn_eddevds    - 2nd order, entropic, input, diag. sym.

       function ddEV = lyngby_nn_eddevds(X, Y, V, W, H12)

       Input:  X      Neural network input
               Y      Neural network output
               W      Output weights
               H12    One minus Hidden layer in 2nd power

       Output: ddEV   Derivative, a vector

       'Symmetric' diagonal approximation to the second order
       derivative of the entropic error function with respect 
       to the input weights.

       H12 can be computed as (1-H.^2)

       See also: lyngby_nn_eddewd

Cross-Reference Information

This function is called by

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