how to implement neural network for eeg motor imagery classification?

I extracted a 140x16 feature table with each line representing the feature vector of one experiment.Also i have the class labels of the 140 experiments.My intention is to use a neural network to classify my experiments by using half or a percentage of them for training the network and the rest for classification.Can anyone guide me?

Answer 1

[Greg Heath]

If you have c classes, the target columns should be columns of the c-dimension unit matrix eye(c).

 [ I N ]  = size(input) % [ 16 140 ]
 [ c N ] = size(target)  % [c  140 ]

For classification tutorials and examples search BOTH the NEWSREADER and ANSWERS with

 greg patternnet

For documentation and associated unsatisfactory examples:

 help patternnet
 doc patternnet

Hope this helps.

Thank you for formally accepting my answer

Greg