Sparse estimation automatically selects voxels relevant for the decoding of fMRI activity patterns
By Okito Yamashita, Masa-aki Sato, Taku Yoshioka, Frank Tong, Yukiyasu Kamitani. NeuroImage, 2008
371 citations recorded by the source corpus.
Subfields: Cognitive Neuroscience
View Paper: https://www.semanticscholar.org/paper/f7352af90512535eee6fcf62229b510b6d5c6ef7
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- John-Dylan Haynes
- Gaël Varoquaux
- Ender Konukoglu
- Bertrand Thirion
- Douglas N. Greve
- Kaustubh Supekar
- Srikanth Ryali
- Vinod Menon
Citations in the corpus
- A Primer on Pattern-Based Approaches to fMRI: Principles, Pitfalls, and Perspectives. (2015, background): “Voxels that are not informative on their own can contribute to a classification by de-noising or by removing the effects of global variations in unspecific internal states (Haufe et al., 2014; Yamashita et al., 2008).”
- Visual image reconstruction from human brain activity using a combination of multiscale local image decoders. (2008, methodology): “In this study, we adopted a full-Bayesian approach to the estimation of weight parameters (‘‘sparse logistic regression,’’ Yamashita et al., 2008).”
- Identifying Predictive Regions from fMRI with TV-L1 Prior (2013, methodology): “using sparsity inducing norms such as the l1 norm [1].”
- Sparse logistic regression for whole brain classification of fMRI data (2010, methodology): “In comparison, existing methods that use the IRWLS optimization on small ROI data (Yamashita et al., 2008) cannot be scaled for whole-brain analysis.”
- Relevant Feature Set Estimation with a Knock-out Strategy and Random Forests (2015, positive): “The models proposed in Tibshirani (1996), Tipping (2000), Bi et al. (2003), Yamashita et al. (2008), and Sabuncu and Van Leemput (2012) aim to create small and predictive models, where it is assumed a-priori that the number of relevant features will be small.”
- Is Nike female? Exploring the role of sound symbolism in predicting brand name gender (2018, methodology): “We applied a sparsity constraint with automatic relevance determination (Yamashita et al., 2008) to explore the minimal set of features necessary for gender determination, taking into account the fact that the features are over-complete and not interdependent, e.”