Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces

TL;DR

This paper introduces a novel elastic neuromorphic metasurface capable of performing classification tasks by reconfiguring waveguides to manipulate elastic waves, offering a new approach to mechanical computing in challenging environments.

Contribution

It presents the first framework for elastic neuromorphic metasurfaces that perform classification, with reconfigurable layers trained via phase adjustments and activation functions.

Findings

Successfully classifies multiple tasks without remanufacturing

Demonstrates reconfigurability in elastic wave manipulation

Enables complex wave-based computation in mechanical systems

Abstract

The ability of mechanical systems to perform basic computations has gained traction over recent years, providing an unconventional alternative to digital computing in off grid, low power, and severe environments which render the majority of electronic components inoperable. However, much of the work in mechanical computing has focused on logic operations via quasi-static prescribed displacements in origami, bistable, and soft deformable matter. In here, we present a first attempt to describe the fundamental framework of an elastic neuromorphic metasurface that performs distinct classification tasks, providing a new set of challenges given the complex nature of elastic waves with respect to scattering and manipulation. Multiple layers of reconfigurable waveguides are phase-trained via constant weights and trainable activation functions in a manner that enables the resultant wave scattering at the readout location to focus on the correct class within the detection plane. We further demonstrate the neuromorphic system's reconfigurability in performing two distinct tasks, eliminating the need for costly remanufacturing.