wolffd@0: wolffd@0: wolffd@0: wolffd@0: Netlab Reference Manual demmlp1 wolffd@0: wolffd@0: wolffd@0: wolffd@0:

demmlp1 wolffd@0:

wolffd@0:

wolffd@0: Purpose wolffd@0:

wolffd@0: Demonstrate simple regression using a multi-layer perceptron wolffd@0: wolffd@0:

wolffd@0: Synopsis wolffd@0:

wolffd@0:

wolffd@0: demmlp1

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

wolffd@0: Description wolffd@0:

wolffd@0: The problem consists of one input variable x and one target variable wolffd@0: t with data generated by sampling x at equal intervals and then wolffd@0: generating target data by computing sin(2*pi*x) and adding Gaussian wolffd@0: noise. A 2-layer network with linear outputs is trained by minimizing a wolffd@0: sum-of-squares error function using the scaled conjugate gradient optimizer. wolffd@0: wolffd@0:

wolffd@0: See Also wolffd@0:

wolffd@0: mlp, mlperr, mlpgrad, scg

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

wolffd@0: