Daniel@0: Daniel@0: Daniel@0: Daniel@0: Netlab Reference Manual netgrad Daniel@0: Daniel@0: Daniel@0: Daniel@0:

netgrad Daniel@0:

Daniel@0:

Daniel@0: Purpose Daniel@0:

Daniel@0: Evaluate network error gradient for generic optimizers Daniel@0: Daniel@0:

Daniel@0: Synopsis Daniel@0:

Daniel@0: 
Daniel@0: g = netgrad(w, net, x, t)
Daniel@0: Daniel@0: Daniel@0:

Daniel@0: Description Daniel@0:

Daniel@0: Daniel@0:

g = netgrad(w, net, x, t) takes a weight vector w and a network Daniel@0: data structure net, together with the matrix x of input Daniel@0: vectors and the matrix t of target vectors, and returns the Daniel@0: gradient of the error function evaluated at w. Daniel@0: Daniel@0:

Daniel@0: See Also Daniel@0:

Daniel@0: mlp, neterr, netopt
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: