wolffd@0: function w = netpak(net)
wolffd@0: %NETPAK	Combines weights and biases into one weights vector.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %	W = NETPAK(NET) takes a network data structure NET and combines the
wolffd@0: %	component weight matrices  into a single row vector W. The facility
wolffd@0: %	to switch between these two representations for the network
wolffd@0: %	parameters is useful, for example, in training a network by error
wolffd@0: %	function minimization, since a single vector of parameters can be
wolffd@0: %	handled by general-purpose optimization routines.  This function also
wolffd@0: %	takes into account a MASK defined as a field in NET by removing any
wolffd@0: %	weights that correspond to entries of 0 in the mask.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	NET, NETUNPAK, NETFWD, NETERR, NETGRAD
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: pakstr = [net.type, 'pak'];
wolffd@0: w = feval(pakstr, net);
wolffd@0: % Return masked subset of weights
wolffd@0: if (isfield(net, 'mask'))
wolffd@0:    w = w(logical(net.mask));
wolffd@0: end