Short-Term Memory in Orthogonal Neural Networks
Disordered Systems and Neural Networks
2009-11-10 v1
Abstract
We study the ability of linear recurrent networks obeying discrete time dynamics to store long temporal sequences that are retrievable from the instantaneous state of the network. We calculate this temporal memory capacity for both distributed shift register and random orthogonal connectivity matrices. We show that the memory capacity of these networks scales with system size.
Keywords
Cite
@article{arxiv.cond-mat/0402452,
title = {Short-Term Memory in Orthogonal Neural Networks},
author = {Olivia L. White and Daniel D. Lee and Haim Sompolinsky},
journal= {arXiv preprint arXiv:cond-mat/0402452},
year = {2009}
}
Comments
4 pages, 4 figures, to be published in Phys. Rev. Lett