Combining sparseness and smoothness improves classification accuracy and interpretability
Authors:
- Matthew de BrechtMBMatthew de Brecht
- Noriko YamagishiNYNoriko Yamagishi
- 1 April 2012
- journal article
- Published by Elsevier in NeuroImage
- Vol. 60 (2) , 1550-1561
Abstract
No abstract availableKeywords
Funding Information
- JST PRESTO program
This publication has 20 references indexed in Scilit:
- A topographic latent source model for fMRI dataNeuroImage, 2011
- Total Variation Regularization for fMRI-Based Prediction of BehaviorIEEE Transactions on Medical Imaging, 2011
- The Smooth-Lasso and other ℓ1+ℓ2-penalized methodsElectronic Journal of Statistics, 2011
- Spatial smoothing hurts localization but not information: Pitfalls for brain mappersNeuroImage, 2010
- Prediction and interpretation of distributed neural activity with sparse modelsNeuroImage, 2009
- Visual Image Reconstruction from Human Brain Activity using a Combination of Multiscale Local Image DecodersNeuron, 2008
- Neuromagnetic motor fields accompanying self-paced rhythmic finger movement at different ratesExperimental Brain Research, 2005
- Spatiotemporal mapping of cortical activity accompanying voluntary movements using an event‐related beamforming approachHuman Brain Mapping, 2005
- Bayesian InterpolationNeural Computation, 1992
- Ridge Regression: Biased Estimation for Nonorthogonal ProblemsTechnometrics, 1970