Sparse sign-consistent Johnson-Lindenstrauss matrices: Compression with neuroscience-based constraints

Sparse sign-consistent Johnson-Lindenstrauss matrices: Compression with neuroscience-based constraints

Johnson-Lindenstrauss (JL) matrices implemented by sparse random synaptic connections are thought to be a prime candidate for how convergent pathways in the brain compress information. However, to date, there is no complete mathematical support for such implementations given the constraints of real...

Full description

Bibliographic Details
Main Authors: Allen-Zhu, Zeyuan (Contributor), Gelashvili, Rati (Contributor), Micali, Silvio (Contributor), Shavit, Nir N. (Contributor)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
Format: Article
Language:English
Published: National Academy of Sciences (U.S.), 2015-06-09T15:35:55Z.
Subjects:
Article
Online Access:Get fulltext

Internet

Get fulltext

Similar Items