Short-Term Memory in Orthogonal Neural Networks

Olivia L. White, Daniel D. Lee, and Haim Sompolinsky
Phys. Rev. Lett. 92, 148102 – Published 9 April 2004

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.

  • Figure
  • Figure
  • Figure
  • Figure
  • Received 11 November 2003

DOI:https://doi.org/10.1103/PhysRevLett.92.148102

©2004 American Physical Society

Authors & Affiliations

Olivia L. White1, Daniel D. Lee2, and Haim Sompolinsky1,3

  • 1Harvard University, Cambridge, Massachusetts 02138, USA
  • 2University of Pennsylvania, Philadelphia, Pennsylvania 19104, USA
  • 3Racah Institute of Physics and Center for Neural Computation, Hebrew University, Jerusalem 91904, Israel

Article Text (Subscription Required)

Click to Expand

References (Subscription Required)

Click to Expand
Issue

Vol. 92, Iss. 14 — 9 April 2004

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review Letters

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×