Park Jihee, Kim Gimun, Kim Sungjun
Division of Electronics and Electrical Engineering, Dongguk University, Seoul 04620, South Korea.
Mater Horiz. 2025 May 2. doi: 10.1039/d5mh00275c.
Reservoir computing (RC) is a promising machine learning paradigm that processes input data using a fixed random network. However, implementing both reservoir and readout layers typically requires multiple devices and additional fabrication steps. To overcome this, we introduce a fully integrated RC system based on a vertically stacked Ta/TaO/HfO/W and TiN vertical-resistive random-access memory (VRRAM) structure, which can select short-term and long-term memory in VRRAM structure with different bottom electrodes. The volatile VRRAM serves as a physical reservoir, utilizing its fading memory and nonlinearity to capture temporal dependencies, while the nonvolatile VRRAM functions as a readout network with multi-level storage capability and high linearity. Neuromorphic simulations show that using conductance variations as synaptic weights enables pattern recognition accuracy above 93.14%, successfully replicating biological synaptic behaviors. Finally, the proposed Cyclic RC structure effectively processes temporal patterns, achieving strong performance with an NRMSE of 0.2123 for waveform classification and 0.2377 for Hénon map prediction. These findings underscore the potential of hardware-efficient, short-term memory-based architectures for forecasting nonlinear dynamical systems and advancing neuromorphic computing applications.
储层计算（RC）是一种很有前景的机器学习范式，它使用固定的随机网络处理输入数据。然而，实现储层和读出层通常需要多个器件和额外的制造步骤。为了克服这一问题，我们引入了一种基于垂直堆叠的Ta/TaO/HfO/W和TiN垂直电阻随机存取存储器（VRRAM）结构的完全集成RC系统，该系统可以通过不同的底部电极在VRRAM结构中选择短期和长期记忆。易失性VRRAM用作物理储层，利用其衰退记忆和非线性来捕获时间依赖性，而非易失性VRRAM则作为具有多级存储能力和高线性的读出网络。神经形态模拟表明，将电导变化用作突触权重可使模式识别准确率高于93.14%，成功复制生物突触行为。最后，所提出的循环RC结构有效地处理时间模式，在波形分类中实现了0.2123的归一化均方根误差（NRMSE）和在Hénon映射预测中实现了0.2377的NRMSE，从而展现出强大的性能。这些发现强调了基于硬件高效、基于短期记忆的架构在预测非线性动力系统和推进神经形态计算应用方面的潜力。
