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.

翻译：储层计算是一种高效处理时序数据的机器学习框架，通过从输入信号中提取特征并将其映射到高维空间来实现。物理储层层已通过自旋振荡器、原子开关网络、硅光子模块、铁电晶体管和易失性忆阻器得以实现。然而，这些器件因电阻本质而固有耗能，导致功耗增加。因此，电容式存储器件可提供更节能的方案。本文利用基于易失性仿生膜的忆容器作为储层——其能紧密模拟某些短时突触可塑性功能——通过仿真与实验解决分类任务并分析时序数据。本系统在口语数字分类任务中达到98%准确率，在二阶非线性回归任务中归一化均方误差为0.0012。进一步，为验证器件的实时时序数据处理能力，我们针对癫痫检测的脑电图信号分类任务实现了100%准确率。最重要的是，对于随机输入序列，每个忆容器每个脉冲平均仅消耗41.5fJ能量（与输入电压脉冲宽度无关），在100ms脉冲宽度下平均功率为415fW，较现有先进器件低数个数量级。最后，我们认为忆容器的生物相容性与柔性特质使其极适用于生物环境中的计算与信号处理应用。