Frustrated Arrays of Nanomagnets for Efficient Reservoir Computing

03/16/2021

∙

We simulated our nanomagnet reservoir computer (NMRC) design on benchmark tasks, demonstrating NMRC's high memory content and expressibility. In support of the feasibility of this method, we fabricated a frustrated nanomagnet reservoir layer. Using this structure, we describe a low-power, low-area system with an area-energy-delay product 10^7 lower than conventional RC systems, that is therefore promising for size, weight, and power (SWaP) constrained applications.

READ FULL TEXT

Frustrated Arrays of Nanomagnets for Efficient Reservoir Computing

Reservoir Computing with Planar Nanomagnet Arrays

Hopf Physical Reservoir Computer for Reconfigurable Sound Recognition

Recognition of handwritten MNIST digits on low-memory 2 Kb RAM Arduino board using LogNNet reservoir neural network

An FPGA Implementation of a Time Delay Reservoir Using Stochastic Logic

Reservoir Computing with Superconducting Electronics

Interpretable Design of Reservoir Computing Networks using Realization Theory

Generating Oscillation Activity with Echo State Network to Mimic the Behavior of a Simple Central Pattern Generator

Frustrated Arrays of Nanomagnets for Efficient Reservoir Computing

Related Research

Reservoir Computing with Planar Nanomagnet Arrays

Hopf Physical Reservoir Computer for Reconfigurable Sound Recognition

Recognition of handwritten MNIST digits on low-memory 2 Kb RAM Arduino board using LogNNet reservoir neural network

An FPGA Implementation of a Time Delay Reservoir Using Stochastic Logic

Reservoir Computing with Superconducting Electronics

Interpretable Design of Reservoir Computing Networks using Realization Theory

Generating Oscillation Activity with Echo State Network to Mimic the Behavior of a Simple Central Pattern Generator