wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual mlphdotv wolffd@0: wolffd@0: wolffd@0: wolffd@0:

mlphdotv wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Evaluate the product of the data Hessian with a vector. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0: 
wolffd@0: hdv = mlphdotv(net, x, t, v)
wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: wolffd@0:

hdv = mlphdotv(net, x, t, v) takes an MLP network data structure wolffd@0: net, together with the matrix x of input vectors, the wolffd@0: matrix t of target vectors and an arbitrary row vector v wolffd@0: whose length equals the number of parameters in the network, and wolffd@0: returns the product of the data-dependent contribution to the Hessian wolffd@0: matrix with v. The implementation is based on the R-propagation wolffd@0: algorithm of Pearlmutter. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: mlp, mlphess, hesschek
wolffd@0: Pages: wolffd@0: Index wolffd@0:
wolffd@0:

Copyright (c) Ian T Nabney (1996-9) wolffd@0: wolffd@0: wolffd@0: wolffd@0: