wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual netunpak wolffd@0: wolffd@0: wolffd@0: wolffd@0:

netunpak wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Separates weights vector into weight and bias matrices. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:
wolffd@0: net = netunpak(net, w)
wolffd@0: 
wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: net = netunpak(net, w) takes an net network data structure net and wolffd@0: a weight vector w, and returns a network data structure identical to wolffd@0: the input network, except that the componenet weight matrices have all wolffd@0: been set to the corresponding elements of w. If there is wolffd@0: a mask field in the net data structure, then the weights in wolffd@0: w are placed in locations corresponding to non-zero entries in the wolffd@0: mask (so w should have the same length as the number of non-zero wolffd@0: entries in the mask). wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: netpak, 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: