论文信息 - Frustrated Arrays of Nanomagnets for Efficient Reservoir Computing

Frustrated Arrays of Nanomagnets for Efficient Reservoir Computing

We simulated our nanomagnet reservoir computer (NMRC) design on benchmark tasks, demonstrating NMRC’s high memory content and expressibility. In support of the feasibility of this method, we fabricated a frustrated nanomagnet reservoir layer. Using this structure, we describe a low-power, low-area system with an area-energy-delay product 10 lower than conventional RC systems, that is therefore promising for size, weight, and power (SWaP) constrained applications. Keywords—Reservoir Computing; Nanomagnet; Recurrent Neural Network; Neuromorphic Computing

[1] Henry Markram,et al. Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[2] Harald Haas,et al. Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[3] R. Brockett,et al. Reservoir observers: Model-free inference of unmeasured variables in chaotic systems. , 2017, Chaos.

[4] Joseph S. Friedman,et al. Reservoir Computing with Planar Nanomagnet Arrays , 2020, ArXiv.

[5] Herbert Jaeger,et al. The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[6] Toshiyuki Yamane,et al. Recent Advances in Physical Reservoir Computing: A Review , 2018, Neural Networks.

[7] F. García-Sánchez,et al. The design and verification of MuMax3 , 2014, 1406.7635.

[8] Zhengya Zhang,et al. A fully integrated reprogrammable memristor–CMOS system for efficient multiply–accumulate operations , 2019, Nature Electronics.