Selection, Reduction, and Orthogonalization

We have already mentioned principal components. For our purposes it is enough to say that these new variables are linear combinations of the old variables. The new variables are orthogonal to each other that is, they are completely independent of one another in that there is no redundancy in the information they carry. They are uncorrelated. 

Principal components have been used as input to backpropagation networks with mixed results. In an application to ion mobility 

---