fMRI Analysis via One-class Machine Learning Techniques
David Hardoon and Larry M. Manevitz
In: 19th International Joint Conference on Aritifical Intelligence, 30 JUL - 05 AUG 2005, Edinburgh, Scotland, UK.
We show how one-class compression Neural Networks
and one-class SVM can be applied to fMRI
data to learn the classification of brain activity associated
with a specific motor activity. For comparison
purposes, we use two labeled data and see
what degree of classification ability is lost compared
with the usual two-class SVM.
|EPrint Type:||Conference or Workshop Item (Poster)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Subjects:||Brain Computer Interfaces|
|Deposited By:||David Hardoon|
|Deposited On:||08 August 2005|