Energy-efficient memcapacitive physical reservoir computing system for temporal data processing

Reservoir computing is a highly efficient machine learning framework for processing temporal data by extracting features from the input signal and mapping them into higher dimensional spaces. Physical reservoir layers have been realized using spintronic oscillators, atomic switch networks, silicon photonic modules, ferroelectric transistors, and volatile memristors. However, these devices are intrinsically energy-dissipative due to their resistive nature, which leads to increased power consumption. Therefore, capacitive memory devices can provide a more energy-efficient approach. Here, we leverage volatile biomembrane-based memcapacitors that closely mimic certain short-term synaptic plasticity functions as reservoirs to solve classification tasks and analyze time-series data in simulation and experimentally. Our system achieves a 98% accuracy rate for spoken digit classification and a normalized mean square error of 0.0012 in a second-order non-linear regression task. Further, to demonstrate the device's real-time temporal data processing capability, we demonstrate a 100% accuracy for an electroencephalography (EEG) signal classification problem for epilepsy detection. Most importantly, we demonstrate that for a random input sequence, each memcapacitor consumes on average 41.5fJ of energy per spike, irrespective of the chosen input voltage pulse width, and 415fW of average power for 100 ms pulse width, orders of magnitude lower than the state-of-the-art devices. Lastly, we believe the biocompatible, soft nature of our memcapacitor makes it highly suitable for computing and signal-processing applications in biological environments.