P
Paul Sajda
Researcher at Columbia University
Publications - 261
Citations - 9050
Paul Sajda is an academic researcher from Columbia University. The author has contributed to research in topics: Electroencephalography & EEG-fMRI. The author has an hindex of 45, co-authored 243 publications receiving 8015 citations. Previous affiliations of Paul Sajda include United States Army Research Laboratory & Sarnoff Corporation.
Papers
More filters
Journal Article
Mathematical modeling of retinal pigment epithelium (RPE) autofluorescence (AF) with Gaussian mixture models and non-negative matrix factorization (NMF)
Ansh Johri,Robert Post,Bhaskar Ganti,Amani A. Fawzi,Paul Sajda,Thomas Ach,Christine A. Curcio,Theodore Smith +7 more
Posted Content
Bayesian recurrent state space model for rs-fMRI.
TL;DR: A hierarchical Bayesian recurrent state space model for modeling switching network connectivity in resting state fMRI data is proposed and outperforms current state of the art deep learning method on ADNI2 dataset.
Journal ArticleDOI
Spatiospectral brain networks reflective of improvisational experience.
TL;DR: Using a spatiospectral based inter and intra network connectivity analysis, it is found that improvisers showed a variety of differences in connectivity within and between large-scale cortical networks compared to classically trained musicians, as a function of deviant type.
Proceedings ArticleDOI
Dealing with position uncertainty when training an image search system
Clay D. Spence,Paul Sajda +1 more
TL;DR: This work forms an error function for the supervised learning of image search/detection tasks when the positions of the objects to be found are uncertain or ill-defined, and presents results for neural networks trained to detect clusters of buildings in aerial photographs.
A probabilistic network model for detection, synthesis and compression in mammographic image analysis
TL;DR: A probabilistic network model over image spaces and its broad utility in mammographic image analysis is demonstrated, particularly with respect to computer-aided diagnosis and qualitative assessment of model structure through mammographic synthesis.