wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual mlpbkp wolffd@0: wolffd@0: wolffd@0: wolffd@0:

mlpbkp wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Backpropagate gradient of error function for 2-layer network. wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: g = mlpbkp(net, x, z, deltas)

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

wolffd@0: Description wolffd@0:

wolffd@0: g = mlpbkp(net, x, z, deltas) takes a network data structure wolffd@0: net together with a matrix x of input vectors, a matrix wolffd@0: z of hidden unit activations, and a matrix deltas of the wolffd@0: gradient of the error function with respect to the values of the wolffd@0: output units (i.e. the summed inputs to the output units, before the wolffd@0: activation function is applied). The return value is the gradient wolffd@0: g of the error function with respect to the network wolffd@0: weights. Each row of x corresponds to one input vector. wolffd@0: wolffd@0:

This function is provided so that the common backpropagation algorithm wolffd@0: can be used by multi-layer perceptron network models to compute wolffd@0: gradients for mixture density networks as well as standard error wolffd@0: functions. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: mlp, mlpgrad, mlpderiv, mdngrad

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

wolffd@0: