Publications

Short-term memory in orthogonal neural networks

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.

Authors: Olivia L White; Daniel D Lee; Haim Sompolinsky
Year of publication: 2004
Journal: Physical Review Letters, Volume 92, p.148102 (2004)

Link to publication:

Labs:

“Working memory”