wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual mdngrad wolffd@0: wolffd@0: wolffd@0: wolffd@0:

mdngrad wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Evaluate gradient of error function for Mixture Density Network. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: 
wolffd@0: g = mdngrad(net, x, t)
wolffd@0:

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

wolffd@0: Description wolffd@0:

wolffd@0: wolffd@0: g = mdngrad(net, x, t) takes a mixture density network data wolffd@0: structure net, a matrix x of input vectors and a matrix wolffd@0: t of target vectors, and evaluates the gradient g of the wolffd@0: error function with respect to the network weights. The error function wolffd@0: is negative log likelihood of the target data. Each row of x wolffd@0: corresponds to one input vector and each row of t corresponds to wolffd@0: one target vector. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: mdn, mdnfwd, mdnerr, mdnprob, mlpbkp

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

wolffd@0:

David J Evans (1998) wolffd@0: wolffd@0: wolffd@0: