Short Term Memory Capacity in Networks via the Restricted Isometry Property
arXiv:1307.7970
Abstract
Cortical networks are hypothesized to rely on transient network activity to support short term memory (STM). In this paper 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 non asymptotic 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 recall mistakes. Furthermore, we show that the conditions yielding optimal STM capacity can be embodied in several network topologies, including networks with sparse or dense connectivities.
arXiv comment50 pages, 5 figures
References in corpus (7)
- Beyond Nyquist: Efficient Sampling of Sparse Bandlimited Signals
- Templates for Convex Cone Problems with Applications to Sparse Signal Recovery
- Short-Term Memory in Orthogonal Neural Networks
- Convergence and Rate Analysis of Neural Networks for Sparse Approximation
- Convergence Speed of a Dynamical System for Sparse Recovery
- Suprema of Chaos Processes and the Restricted Isometry Property
- Signal buffering in random networks of spiking neurons: microscopic vs. macroscopic phenomena