Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
2004-02-17
Phys. Rev. Lett. 92, 148102 (2004)
Physics
Condensed Matter
Disordered Systems and Neural Networks
4 pages, 4 figures, to be published in Phys. Rev. Lett
Scientific paper
10.1103/PhysRevLett.92.148102
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.
Lee Daniel D.
Sompolinsky Haim
White Olivia L.
No associations
LandOfFree
Short-Term Memory in Orthogonal Neural Networks does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Short-Term Memory in Orthogonal Neural Networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Short-Term Memory in Orthogonal Neural Networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-237499