Memimpedance-Based Biomolecular Device for Adaptive Physical Reservoir Computing

Artificial neural networks and recurrent neural networks are foundational to machine learning; although successful, their simplified components lack the intricate dynamics and high functional density of biological neural networks, limiting their efficiency. Physical reservoir computing (PRC) offers an alternative by leveraging the intrinsic dynamics of physical systems while restricting training to the readout layer. However, two significant shortcomings hinder the PRC's efficacy: the memory-nonlinearity trade-off, where increasing nonlinearity reduces memory capacity, and limited timescale adaptability, constraining it to contrived task-device matching. This work presents a biomolecular PRC system that integrates heterogeneous nodes with complementary memimpedance properties using droplet interface bilayers. The system combines ion channel-based memristive (nonlinear, fast-switching) and biomembrane-based memcapacitive (linear, slow-switching) nodes within a single device, addressing the trade-off and enabling multiscale temporal processing. Predicting a second-order nonlinear system is demonstrated to address the trade-off, achieving a normalized mean square error of 0.176 with the hybrid system outperforming memristive and memcapacitive reservoirs. Additionally, two real-time classification tasks validate the system's ability to process signals across temporal scales, achieving 100% accuracy in both tasks. This approach expands PRC's applicability across diverse tasks without preoptimization, underscoring the potential of PRC and soft biomolecular materials for adaptive energy-efficient computing.