scispace - formally typeset
R

Rogers F. Silva

Researcher at Georgia Institute of Technology

Publications -  49
Citations -  1808

Rogers F. Silva is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Independent component analysis & Infomax. The author has an hindex of 14, co-authored 43 publications receiving 1459 citations. Previous affiliations of Rogers F. Silva include University of New Mexico & The Mind Research Network.

Papers
More filters
Journal ArticleDOI

Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning

TL;DR: In this article, the authors conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for deep learning for brain imaging data analysis.
Journal ArticleDOI

Independent Component Analysis for Brain fMRI Does Indeed Select for Maximal Independence

TL;DR: It is shown that these experiments fall short of proving claims that two independent component analysis algorithms, Infomax and FastICA, select for sparsity rather than independence, and that the ICA algorithms are indeed doing what they are designed to do: identify maximally independent sources.
Proceedings ArticleDOI

The tenth annual mlsp competition: schizophrenia classification challenge

TL;DR: Details about the competition setup, the winning strategies, and basic analyses of the submitted entries are reviewed to provide basic analyses and a discussion of the advances made to the neuroimaging and machine learning fields are discussed.
Journal ArticleDOI

Correction: Independent Component Analysis for Brain fMRI Does Indeed Select for Maximal Independence

TL;DR: This article was republished on October 23, 2013 because of missing equations.