input to a custom network

I am designing a neural network with 4 inputs and 2 layers including the output layer. the input database is in an excel document and is of the matrix which has 97rows and 5 columns. This is in one sheet and I have 11 such sheets. I am able to import the data to the M-file; however I am unable to give it as an input to the neural network to train. How am I supposed to give my database as the input? Also using trainlm, it gives me an error saying zero input delay. How am I supposed to use the train function [net tr] if my and the input database is all those 11 sheets and the target is just one column?

Answer 1

[Greg Heath]

% Read in the 11 sheets and combine to obtain a data matrix with size(data) = [ 5 1067 ] (1067 = 11*97)

close all, clear all, clc

input = data(1:4,:);

target = data(5,:);

[ I N ] = size(input) % [ 4 1067 ]

[ O N ] = size(target) % [ 1 1067 ]

% I = 4

% O = 1

% N = 1067

% input = randn( I ,N );

% hidden= sum(input);

% target = 1 + hidden+ hidden.^2 ;

% plot(hidden,target,'o')

% Using the NN default data division

Ntrn = N - 2*round(0.15*N) % 747

Neq = Ntrn*O % 747 Number of training equations

% Assuming an I-H-O = 4-H-1 FFMLP for regression or curvefitting, the number of unknown weights to be estimated by the 747 equations is

% Nw = (I+1)*H+(H+1)*O = O+(I+O+1)*H = 1+6*H.

% Typically, Neq > Nw is required although Neq >> Nw is desired. The resulting upper bound on H is

Hub = floor((Neq-O)/(I+O+1)) % 124

% Therefore, the default value H = 10 << Hub = 124 is a reasonable first choice.

net = fitnet;

net.trainParam.goal = var(target)/100;

[net tr Y E ] = train(net,input,target);

Hope this helps.

Greg