|
Abstract
|
|
|---|---|
| This paper describes the main characteristics of our approach to the ICANN- 2011 Mind reading from MEG - PASCAL Challenge. The distinguished features of our method are: 1) The use of different sources of information as input to the classi?ers. We simultaneously use information coming from raw data, channels correlations, mutual information between channels, and channel interactions graphs as features for the classi?ers. 2) The use of ensemble of classi?ers based on regularized multi-logistic regression, regression trees, and an af?nity propagation based classi?er. | |
|
International
|
Si |
|
Congress
|
International Conference on Artificial Neural Networks |
|
|
960 |
|
Place
|
Espoo, Finland |
|
Reviewers
|
Si |
|
ISBN/ISSN
|
978-952-60-4456-9 |
|
|
|
|
Start Date
|
14/06/2011 |
|
End Date
|
17/06/2011 |
|
From page
|
25 |
|
To page
|
30 |
|
|
Proceedings of the ICANN/PASCAL2 Challenge: MEG Mind Reading |