PNAS Plus Significance Statements
PNAS Plus Significance Statements
Demba Ba,B. Babadi,18 Authors,Krzysztof Palczewski
2014 · DOI: 10.1073/pnas.ss11150
Proceedings of the National Academy of Sciences of the United States of America · 278 Citations
TLDR
A new Bayesian spectral decomposition framework—spectrotemporal pursuit—is developed to compute spectral estimates that are smooth in time and sparse in frequency and a statistical interpretation of sparse recovery is used to derive efficient algorithms for computing spectrotemporal pursuit spectral estimates.