mlphdotv

Purpose

Evaluate the product of the data Hessian with a vector.

Synopsis

hdv = mlphdotv(net, x, t, v)

Description

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

See Also

mlp, mlphess, hesschek
Pages: Index

Copyright (c) Ian T Nabney (1996-9)