English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent interest has developed around the problem of dynamic compressedsensing, or the recovery of time-varying, sparse signals from limitedobservations. In this paper, we study how the dynamics of recurrent networks,formulated as general dynamical systems, mediate the recoverability of suchsignals. We specifically consider the problem of recovering a high-dimensionalnetwork input, over time, from observation of only a subset of the networkstates (i.e., the network output). Our goal is to ascertain how the networkdynamics lead to performance advantages, particularly in scenarios where boththe input and output are corrupted by disturbance and noise, respectively. Forthis scenario, we develop bounds on the recovery performance in terms of thedynamics. Conditions for exact recovery in the absence of noise are alsoformulated. Through several examples, we use the results to highlight howdifferent network characteristics may trade off toward enabling dynamiccompressed sensing and how such tradeoffs may manifest naturally in certainclasses of neuronal networks.

Analysis of Recurrent Linear Networks for Enabling Compressed Sensing of Time-Varying Signals