ME697 Assignment #2 Due: 2/23/10 Spring 2012 1.Construct a three layer feedforward neural network (one hidden layer) using the back propagation learning algorithm to approximate the following two input and one output function: (10 pts) 2222121212(1))235111211211(, ) 3(1 )10()5333,331xxxxFxxx ex x ee−−+−−−+−=−−−−≤ ≤xxxShow the error reduction graphically with the increasing number of hidden nodes using the following criterion: ∑∑==−−=NkNkdkdkykdNDEI1212)()()(2.Construct a radial basis function neural network for the sample problem given in Problem 1, using the Gaussian basis function. Use the linear least square technique to update the
This is the end of the preview. Sign up
access the rest of the document.
This note was uploaded on 02/22/2012 for the course ME 697 taught by Professor Staff during the Fall '08 term at Purdue.