how to classify after doing PCA on the input data?

I need to classify eeg data using pca and neural network into 5 classes. So far, i have done the pca using the matlab function, but i am confused in what to input to the neural network? What should be the target vector and the input vector that should be given to the neural network. I am a beginner in this, and i have been searching alot for this, but no success.

Answer 1

[Greg Heath]

 1. How may cases do you have for each class?
 2. target vectors are 5-dimensional {0,1} column unit vectors.
 3. Use PLS instead of PCA for input dimensionality reduction
 4. What are the  dimensions of the input coordinates before and after dimensionality reduction?

Hope this helps.

Thank you for formally accepting my answer

Greg