wolffd@0: function w = mlppak(net)
wolffd@0: %MLPPAK	Combines weights and biases into one weights vector.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %	W = MLPPAK(NET) takes a network data structure NET and combines the
wolffd@0: %	component weight matrices bias vectors into a single row vector W.
wolffd@0: %	The facility to switch between these two representations for the
wolffd@0: %	network parameters is useful, for example, in training a network by
wolffd@0: %	error function minimization, since a single vector of parameters can
wolffd@0: %	be handled by general-purpose optimization routines.
wolffd@0: %
wolffd@0: %	The ordering of the paramters in W is defined by
wolffd@0: %	  w = [net.w1(:)', net.b1, net.w2(:)', net.b2];
wolffd@0: %	 where W1 is the first-layer weight matrix, B1 is the first-layer
wolffd@0: %	bias vector, W2 is the second-layer weight matrix, and B2 is the
wolffd@0: %	second-layer bias vector.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	MLP, MLPUNPAK, MLPFWD, MLPERR, MLPBKP, MLPGRAD
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: % Check arguments for consistency
wolffd@0: errstring = consist(net, 'mlp');
wolffd@0: if ~isempty(errstring);
wolffd@0:   error(errstring);
wolffd@0: end
wolffd@0: 
wolffd@0: w = [net.w1(:)', net.b1, net.w2(:)', net.b2];
wolffd@0: