Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual netunpak Daniel@0: Daniel@0: Daniel@0: Daniel@0:

netunpak Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

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

Daniel@0: Synopsis Daniel@0:

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

Daniel@0: Description Daniel@0:

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

Daniel@0: See Also Daniel@0:

Daniel@0: netpak, netfwd, neterr, netgrad
Daniel@0: Pages: Daniel@0: Index Daniel@0:
Daniel@0:

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