[Master Index]
[Index for export/lyngby]
# lyngby_nn_qddevs

## (export/lyngby/lyngby_nn_qddevs.m)

### Function Synopsis

ddEV = lyngby_nn_qddevs(X, V, W, H12)

### Help text

lyngby_nn_qddevs - 2nd der., quadratic, input, gauss approx.
function ddEV = lyngby_nn_qddevs(X, V, W, H12)
Input: X Neural network input
V Input weights
W Output weights
H12 (1-tanh(XV).^2)
Output: ddEV Derivative as a Hessian matrix
Gauss-Newton (symmetric) approximation to the second order
derivative of the qaudratic error function with respect to the
input weights in the neural network.

### Cross-Reference Information

This function is called by

Produced by mat2html on Wed Jul 29 15:43:40 2009

Cross-Directory links are: OFF