Multistable Physical Neural Networks

Abstract

Artificial neural networks (ANNs), which are inspired by the brain, are a central pillar in the ongoing breakthrough in artificial intelligence. In recent years, researchers have examined mechanical implementations of ANNs, denoted as physical neural networks (PNNs). PNNs offer the opportunity to view common materials and physical phenomena as networks, and to associate computational power with them. In this work, mechanical bistability is incorporated into PNNs, enabling memory and a direct link between computation and physical action. To achieve this, an interconnected network of bistable liquid-filled chambers is considered. All possible equilibrium configurations or steady-states are first mapped, and then their stability is examined. Building on these maps, both global and local algorithms for training multistable PNNs are implemented. These algorithms enable to systematically examine the network's capability to achieve stable output states and thus the network's ability to perform computational tasks. By incorporating PNNs and multistability, it is possible to design structures that mechanically perform tasks typically associated with electronic neural networks, while directly obtaining physical actuation. The insights gained from this study pave the way for the implementation of intelligent structures in smart tech, metamaterials, medical devices, soft robotics, and other fields.