Short-term memory capacity in networks via the restricted isometry property

Adam S. Charles, Han Lun Yap, Christopher J. Rozell

Research output: Contribution to journalLetterpeer-review

Abstract

Cortical networks are hypothesized to rely on transient network activity to support short-term memory (STM). In this letter, we study the capacity of randomly connected recurrent linear networks for performing STM when the input signals are approximately sparse in some basis.We leverage results from compressed sensing to provide rigorous nonasymptotic recovery guarantees, quantifying the impact of the input sparsity level, the input sparsity basis, and the network characteristics on the system capacity. Our analysis demonstrates that network memory capacities can scale superlinearly with the number of nodes and in some situations can achieve STM capacities that are much larger than the network size. We provide perfect recovery guarantees for finite sequences and recovery bounds for infinite sequences. The latter analysis predicts that network STM systems may have an optimal recovery length that balances errors due to omission and recallmistakes. Furthermore,weshow that the conditions yielding optimalSTM capacity can be embodied in several network topologies, including networks with sparse or dense connectivities.

Original languageEnglish (US)
Pages (from-to)1198-1235
Number of pages38
JournalNeural Computation
Volume26
Issue number6
DOIs
StatePublished - 2014
Externally publishedYes

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Short-term memory capacity in networks via the restricted isometry property'. Together they form a unique fingerprint.

Cite this