Description
[c,cm,ind,per] = confusion(targets,outputs)
takes
these values:
targets  S byQ matrix,
where each column vector contains a single 1 value,
with all other elements 0 . The index of the 1 indicates
which of S categories that vector represents.

outputs  S byQ matrix,
where each column contains values in the range [0,1] .
The index of the largest element in the column indicates which of S categories
that vector represents.

and returns these values:
c  Confusion value = fraction of samples misclassified 
cm  S byS confusion
matrix, where cm(i,j) is the number of samples
whose target is the i th class that was classified
as j

ind  S byS cell array,
where ind{i,j} contains the indices of samples
with the i th target class, but j th
output class

per  S by4 matrix,
where each row summarizes four percentages associated with the i th
class:
per(i,1) false negative rate
= (false negatives)/(all output negatives)
per(i,2) false positive rate
= (false positives)/(all output positives)
per(i,3) true positive rate
= (true positives)/(all output positives)
per(i,4) true negative rate
= (true negatives)/(all output negatives) 
[c,cm,ind,per] = confusion(TARGETS,OUTPUTS)
takes
these values:
targets  1 byQ vector of
1/0 values representing membership

outputs  S byQ matrix,
of value in [0,1] interval, where values greater
than or equal to 0.5 indicate class membership

and returns these values:
c  Confusion value = fraction of samples misclassified 
cm  2 by2 confusion
matrix

ind  2 by2 cell array,
where ind{i,j} contains the indices of samples
whose target is 1 versus 0 ,
and whose output was greater than or equal to 0.5 versus
less than 0.5

per  2 by4 matrix where
each i th row represents the percentage of false
negatives, false positives, true positives, and true negatives for
the class and outofclass

Examples
[x,t] = simpleclass_dataset;
net = patternnet(10);
net = train(net,x,t);
y = net(x);
[c,cm,ind,per] = confusion(t,y)