Randomness and isometries in echo state networks and compressed sensing

02/05/2018
by   Ashley Prater-Bennette, et al.
0

Although largely different concepts, echo state networks and compressed sensing models both rely on collections of random weights; as the reservoir dynamics for echo state networks, and the sensing coefficients in compressed sensing. Several methods for generating the random matrices and metrics to indicate desirable performance are well-studied in compressed sensing, but less so for echo state networks. This work explores any overlap in these compressed sensing methods and metrics for application to echo state networks. Several methods for generating the random reservoir weights are considered, and a new metric, inspired by the restricted isometry property for compressed sensing, is proposed for echo state networks. The methods and metrics are investigated theoretically and experimentally, with results suggesting that the same types of random matrices work well for both echo state network and compressed sensing scenarios, and that echo state network classification accuracy is improved when the proposed restricted isometry-like constants are close to 1.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2020

On Compressed Sensing Matrices Breaking the Square-Root Bottleneck

Compressed sensing is a celebrated framework in signal processing and ha...
research
10/20/2021

Cascaded Compressed Sensing Networks: A Reversible Architecture for Layerwise Learning

Recently, the method that learns networks layer by layer has attracted i...
research
01/14/2018

Compressed Neighbour Discovery using Sparse Kerdock Matrices

We study the network-wide neighbour discovery problem in wireless networ...
research
08/05/2023

OrcoDCS: An IoT-Edge Orchestrated Online Deep Compressed Sensing Framework

Compressed data aggregation (CDA) over wireless sensor networks (WSNs) i...
research
04/13/2020

Low-Cost and High-Throughput Testing of COVID-19 Viruses and Antibodies via Compressed Sensing: System Concepts and Computational Experiments

Coronavirus disease 2019 (COVID-19) is an ongoing pandemic infectious di...
research
04/06/2019

Optimal Sampling of Water Distribution Network Dynamics using Graph Fourier Transform

Water Distribution Networks (WDNs) are critical infrastructures that ens...
research
05/11/2017

The Network Nullspace Property for Compressed Sensing of Big Data over Networks

We adapt the nullspace property of compressed sensing for sparse vectors...

Please sign up or login with your details

Forgot password? Click here to reset