Hi
usually when it is a 2 vector inputs, so it is easily to visualise the successful classification and it is relying on linearly or nonlinearly seperating the output using svm and plot it into a graph as input2 vs input1
similarly, a 3-vector input would involve seperating the ouput states with a plane surface. thereafter, visualisation becomes more difficult when you have for example a 20 vector inputs.
in my phd, i classify the data correctly using SVM, and when plotting it i only consider 2 vector inputs at a time....
it is a basic way, and def not the optimum way of doing things.
an good alternative, is by applying PCA and use the scores of PCA to run SVM and display the decision boundaries based on SVM's results on the PCA score. which i haven't applied.
kinds regards
>>> [log in to unmask] 02/23/05 3:34 am >>>
Hello,
Is there any toolbox that allows plotting of 2 classes and the separating
hyperplane for samples that have more than 3 attributes/dimensions?
Sincerely,
Monika Ray
***********************************************************************
The sweetest songs are those that tell of our saddest thought...
Computational Intelligence Centre, Washington University St. louis, MO
**********************************************************************
This message has been checked for viruses but the contents of an attachment
may still contain software viruses, which could damage your computer system:
you are advised to perform your own checks. Email communications with the
University of Nottingham may be monitored as permitted by UK legislation.
|