PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

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.

Abstract

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.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Brain Computer Interfaces
ID Code:1043
Deposited By:David Hardoon
Deposited On:08 August 2005