Short-Term Memory in Orthogonal Neural Networks
Top Cited Papers
- 9 April 2004
- journal article
- research article
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 92 (14) , 148102
- https://doi.org/10.1103/physrevlett.92.148102
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
All Related Versions
This publication has 4 references indexed in Scilit:
- Temporal integration by calcium dynamics in a model neuronNature Neuroscience, 2003
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- Synaptic reverberation underlying mnemonic persistent activityTrends in Neurosciences, 2001
- How the brain keeps the eyes stillProceedings of the National Academy of Sciences, 1996