Intrinsic Voltage Offsets in Memcapacitive Bio-Membranes Enable High-Performance Physical Reservoir Computing

TL;DR

This paper introduces a novel heterogeneous memcapacitor-based reservoir computer that exploits intrinsic voltage offsets to achieve high accuracy in predicting nonlinear and chaotic systems without complex input encoding.

Contribution

It presents a new PRC design leveraging internal voltage offsets for efficient high-dimensional transformations, surpassing previous methods in accuracy and simplicity.

Findings

Achieved extremely low prediction error (0.00018) for nonlinear systems.

Predicted chaotic Hénon map with low normalized RMSE (0.080).

Demonstrated high performance without input encoding methods.

Abstract

Reservoir computing is a brain-inspired machine learning framework for processing temporal data by mapping inputs into high-dimensional spaces. Physical reservoir computers (PRCs) leverage native fading memory and nonlinearity in physical substrates, including atomic switches, photonics, volatile memristors, and, recently, memcapacitors, to achieve efficient high-dimensional mapping. Traditional PRCs often consist of homogeneous device arrays, which rely on input encoding methods and large stochastic device-to-device variations for increased nonlinearity and high-dimensional mapping. These approaches incur high pre-processing costs and restrict real-time deployment. Here, we introduce a novel heterogeneous memcapacitor-based PRC that exploits internal voltage offsets to enable both monotonic and non-monotonic input-state correlations crucial for efficient high-dimensional transformations. We demonstrate our approach's efficacy by predicting a second-order nonlinear dynamical system with an extremely low prediction error (0.00018). Additionally, we predict a chaotic H\'enon map, achieving a low normalized root mean square error (0.080). Unlike previous PRCs, such errors are achieved without input encoding methods, underscoring the power of distinct input-state correlations. Most importantly, we generalize our approach to other neuromorphic devices that lack inherent voltage offsets using externally applied offsets to realize various input-state correlations. Our approach and unprecedented performance are a major milestone towards high-performance full in-materia PRCs.