MATLAB: Patternnet for multi-dimensional classification

Deep Learning Toolboxpatternet

Hello,

I'm trying to develop a neural network for classification of 2 non mutually exclusive outputs, based on 1 input.

Using the standard parameters for the patternnet, I had in the 2 outputs numbers between 0 and 1, summing up to 1. It looked like it was working as they were mutually exclusive, even thought I had in my training matrix cases with both outputs in state 1.

I changed the output transfer function to logsig and removed the default { -1, 1} mapminmax output transformation (after reading this in another topic), but with this I had a very poor training performance…

Any comments would be very appreciated! Thanks.

Best Answer

The training target should have nonnegative entries that sum to 1 and can be interpreted as prior probabilities.

0 and 1 are only used if the classes are mutually exclusive.

The output target should also have nonnegative entries that sum to 1 (e.g., via SOFTMAX) and can be interpreted as posterior probabilities.

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Solutions

MATLAB: How to calculate the output error for feedforwardnet

For classification of c classes, the target columns should be columns of the c-dimensional unit matrix.

class = vec2ind(target);

N = length(class);

....

assignedclass = vec2ind(output);

Nerr = sum(assignedclass ~= class);

PCTerr = 100*Nerr/N

Hope this helps.

Thank you for formally accepting my answer.

Greg

MATLAB: Neural Network non mutually exclusive cross entropy loss function

The target matrix columns should contain the

        NON-NEGATIVE UNIT SUM APRIORI CLASS PROBABILITIES !!!

See any text regarding statistical classification

Hope this helps

Thank you for formally accepting my answer

Greg

Best Answer

Related Solutions

MATLAB: How to calculate the output error for feedforwardnet

MATLAB: Neural Network non mutually exclusive cross entropy loss function

Related Question