wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual netderiv wolffd@0: wolffd@0: wolffd@0: wolffd@0:

netderiv wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Evaluate derivatives of network outputs by weights generically. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: g = netderiv(w, net, x)

wolffd@0: wolffd@0: wolffd@0:

wolffd@0: Description wolffd@0:

wolffd@0: wolffd@0:

g = netderiv(w, net, x) takes a weight vector w and a network wolffd@0: data structure net, together with the matrix x of input wolffd@0: vectors, and returns the wolffd@0: gradient of the outputs with respect to the weights evaluated at w. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: netevfwd, netopt

wolffd@0: Pages: wolffd@0: Index wolffd@0:

wolffd@0: