wolffd@0: function g = netderiv(w, net, x)
wolffd@0: %NETDERIV Evaluate derivatives of network outputs by weights generically.
wolffd@0: %
wolffd@0: %	Description
wolffd@0: %
wolffd@0: %	G = NETDERIV(W, NET, X) takes a weight vector W and a network data
wolffd@0: %	structure NET, together with the matrix X of input vectors, and
wolffd@0: %	returns the gradient of the outputs with respect to the weights
wolffd@0: %	evaluated at W.
wolffd@0: %
wolffd@0: %	See also
wolffd@0: %	NETEVFWD, NETOPT
wolffd@0: %
wolffd@0: 
wolffd@0: %	Copyright (c) Ian T Nabney (1996-2001)
wolffd@0: 
wolffd@0: fstr = [net.type, 'deriv'];
wolffd@0: net = netunpak(net, w);
wolffd@0: g = feval(fstr, net, x);