In recent neuroscience research, it is of significant importance to develop an efficient method to predict subject's behaviors or cognitive states from his brain activities for both its applications and methodology. In ATR Computational Neuroscience Laboratories, we have developed "sparse estimation algorithms" and successfully applied them to various problems. There are several merits in sparse estimation algorithms
- they are applicable for problems with small number of samples and high (more than several thousand) dimensional data,
- they avoid overfitting to some extent,
- they make a result more interpretable.
In addition, the sparse estimation algorithms here requires no parameter tuning, thus you can apply these algorithms to wide range of data sets immediately.
In the following link, we collect MATLAB toolboxes for sparse estimation algorithms that have been developed by our group and collaborators. We provide three sparse estimation toolboxes for regression problems and one for classification problems. Please apply one of three regression toolboxes when your behavior variable takes continuous value and the classification toolbox when your behavior variable is a categorical variable. Please try them for your data anyway.
introduction of the sparse estimation library (PDF/Japanese 433KB)
contents of this site
Sparse estimation methods for regression problems
Sparse regression toolbox written by M. Sato (ATR)
Variational Bayesian sparse regression with ARD prior
Sparse regression toolbox written by Ganesh Gowrishankar (ATR)
Sparse regression by MAP-EM algorithm with ARD prior
Sparse regression toolbox written by Stefan Schaal (USC)
Variational Bayesian Least-Squares
Sparse estimation methods for classification problems
Sparse classification toolbox written by Okito Yamasita (ATR)
Sparse logistic regression for binary classification
Sparse logistic regression for multiclass classification
ATR Computational Neuroscience Laboratories
Department of Computational Brain Imaging
COPYRIGHT 2009 (C) ATR ALL RIGHT RESERVED.