Batch version of the back-propagation algorithm.
％ Given a set of corresponding input-output pairs and an initial network
％ [W1,W2,critvec,iter]=batbp(NetDef,W1,W2,PHI,Y,trparms) trains the
％ network with backpropagation.
％
％ The activation functions must be either linear or tanh. The network
％ architecture is defined by the matrix NetDef consisting of two
％ rows. The first row specifies the hidden layer while the second
％ specifies the output layer.
％
This function calculates Akaike s final prediction error
％ estimate of the average generalization error.
％
％ [FPE,deff,varest,H] = fpe(NetDef,W1,W2,PHI,Y,trparms) produces the
％ final prediction error estimate (fpe), the effective number of
％ weights in the network if the network has been trained with
％ weight decay, an estimate of the noise variance, and the Gauss-Newton
％ Hessian.
％
％ Train a two layer neural network with the Levenberg-Marquardt
％ method.
％
％ If desired, it is possible to use regularization by
％ weight decay. Also pruned (ie. not fully connected) networks can
％ be trained.
％
％ Given a set of corresponding input-output pairs and an initial
％ network,
％ [W1,W2,critvec,iteration,lambda]=marq(NetDef,W1,W2,PHI,Y,trparms)
％ trains the network with the Levenberg-Marquardt method.
％
％ The activation functions can be either linear or tanh. The
％ network architecture is defined by the matrix NetDef which
％ has two rows. The first row specifies the hidden layer and the
％ second row specifies the output layer.
This function calculates Akaike s final prediction error
％ estimate of the average generalization error for network
％ models generated by NNARX, NNOE, NNARMAX1+2, or their recursive
％ counterparts.
％
％ [FPE,deff,varest,H] = nnfpe(method,NetDef,W1,W2,U,Y,NN,trparms,skip,Chat)
％ produces the final prediction error estimate (fpe), the effective number
％ of weights in the network if it has been trained with weight decay,
％ an estimate of the noise variance, and the Gauss-Newton Hessian.
％
