Focused surface acoustic wave induced nano-oscillator based reservoir computing
Focused surface acoustic wave induced nano-oscillator based reservoir computing
复制标题
DOI：
10.1063/5.0110769
复制
发表时间：
2022-09-05
影响因子：
4
通讯作者：
Atulasimha, Jayasimha
中科院分区：
文献类型：
--
作者：
Chowdhury, Md. Fahim F.;Al Misba, Walid;Atulasimha, Jayasimha
我们使用微磁模拟证明，由表面声波（SAW）激发的纳米磁体阵列可以用作储层。输入纳米磁体由聚焦声表面波激发并与多个纳米磁体耦合，其中七个纳米磁体用作输出纳米磁体。为了评估记忆效应和计算能力，我们分别研究了短期记忆（STM）和奇偶校验（PC）能力。 SAW（4 GHz 载波频率）幅度经过调制，可提供一系列 100 MHz 频率的正弦波和方波。通过读取其磁化状态的包络来处理所选输出纳米磁体的响应，该包络用于使用回归方法训练输出权重。分类时，使用 100 个方波和正弦波样本的随机序列，其中 80% 用于训练，其余用于测试。我们实现了 100% 的训练和 100% 的测试准确率。计算得出的平均 STM 和 PC 分别为 ∼4.69 和 ∼5.39 位，这表明所提出的声学驱动纳米磁体振荡器阵列非常适合物理储层计算应用。能量耗散比基于 CMOS 的回声状态网络低 & SIM;2.5 倍。此外，该水库能够准确预测 Mackey-Glass 时间序列，最多可提前几个时间步。最后，使用高频 SAW 的能力使纳米磁体储层可扩展到小尺寸，并且以较低频率 (100 MHz) 调制包络的能力增加了对不同信号进行编码的灵活性，超出了此处演示的正弦/方波分类和 Mackey-Glass 预测任务。由 AIP Publishing 独家许可出版。
We demonstrate using micromagnetic simulations that a nanomagnet array excited by surface acoustic waves (SAWs) can work as a reservoir. An input nanomagnet is excited with focused SAW and coupled to several nanomagnets, seven of which serve as output nanomagnets. To evaluate memory effect and computing capability, we study the short-term memory (STM) and parity check (PC) capacities, respectively. The SAW (4 GHz carrier frequency) amplitude is modulated to provide a sequence of sine and square waves of 100 MHz frequency. The responses of the selected output nanomagnets are processed by reading the envelope of their magnetization states, which is used to train the output weights using the regression method. For classification, a random sequence of 100 square and sine wave samples is used, of which 80% are used for training, and the rest are used for testing. We achieve 100% training and 100% testing accuracy. The average STM and PC are calculated to be & SIM;4.69 and & SIM;5.39 bits, respectively, which is indicative of the proposed acoustically driven nanomagnet oscillator array being well suited for physical reservoir computing applications. The energy dissipation is & SIM;2.5 times lower than a CMOS-based echo-state network. Furthermore, the reservoir is able to accurately predict Mackey-Glass time series up to several time steps ahead. Finally, the ability to use high frequency SAW makes the nanomagnet reservoir scalable to small dimensions, and the ability to modulate the envelope at a lower frequency (100 MHz) adds flexibility to encode different signals beyond the sine/square waves classification and Mackey-Glass predication tasks demonstrated here. Published under an exclusive license by AIP Publishing.