MATLAB: How to generate simple feed-forward code with accuracy

Question

Hai. I am new to Matlab and Artificial Intelligent field. Therefore, I need your kind help to generate a simple feed forward for classification. I tried to use simple feed forward coding in Matlab R2012b but I do not know how to check the accuracy. I ve tried different code but it always lead to many errors. I do not know how to fix. I have attached my extracted features data. I need to classify 4 classes.

Previously, I have used this feed-fwd coding but i dont know how to check the accuracy. Plus, what is mean by the performance value?

clear all;

clc;

x = xlsread('mmg_selinp.xlsx');

t = xlsread('mmg_masout.xlsx');

x = x';

t = t';

net = feedforwardnet([15 10],'traingdx')

net = train(net,x,t);

view(net)

y = net(x);

perf = perform(net,y,t)

Sorry, i am really new to Matlab and AI. Your help is highly appreciated. I am not sure whether there s problem with my data. Thank you in advance.

Answer 1

Use patternnet for classification.

 help patternnet
 doc patternnet

For c classes, the target columns are obtained from eye(c).

Search the NEWSGROUP and ANSWERS using

 greg patternnet

Thank you for formally accepting my answer

Greg

PS Include "neural" in you tags