wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual netpak wolffd@0: wolffd@0: wolffd@0: wolffd@0:

netpak wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Combines weights and biases into one weights vector. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0: 
wolffd@0: w = netpak(net)
wolffd@0:
wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: w = netpak(net) takes a network data structure net and wolffd@0: combines the component weight matrices into a single row wolffd@0: vector w. The facility to switch between these two wolffd@0: representations for the network parameters is useful, for example, in wolffd@0: training a network by error function minimization, since a single wolffd@0: vector of parameters can be handled by general-purpose optimization wolffd@0: routines. This function also takes into account a mask defined wolffd@0: as a field in net by removing any weights that correspond to wolffd@0: entries of 0 in the mask. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: net, netunpak, netfwd, neterr, netgrad
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: