MEG Decoding with Hierarchical Combination of Logistic Regression and Random Forests
Research output: Other contribution › Scientific
|Type||Technical report of our 2nd place submission to the DecMeg 2014 competition at Kaggle.com|
|Number of pages||10|
|Publication status||Published - 2014|
This document describes the solution of the second place team in the DecMeg2014 brain decoding competition hosted at Kaggle.com. The model is a hierarchical combination of logistic regression and random forest. The first layer consists of a collection of 337 logistic regression classifiers, each using data either from a single sensor (31 features) or data from a single time point (306 features). The resulting probability estimates are fed to a 1000-tree random forest, which makes the final decision. In order to adjust the model to an unlabeled subject, the classifier is trained iteratively: After initial training, the model is retrained with unlabeled samples in the test set using their predicted labels from first iteration.