Riou M, Torrejon J, Garitaine B, Araujo F Abreu, Bortolotti P, Cros V, Tsunegi S, Yakushiji K, Fukushima A, Kubota H, Yuasa S, Querlioz D, Stiles M D, Grollier J
Unité Mixte de Physique CNRS, Thales,Université Paris-Sud, Université Paris-Saclay, 91767 Palaiseau, France.
National Institute of Advanced Industrial Science and Technology (AIST), Spintronic Research Center, Tsukuba, Ibaraki 305-8568, Japan.
Phys Rev Appl. 2019;12(2). doi: 10.1103/physrevapplied.12.024049.
The recent demonstration of neuromorphic computing with spin-torque nano-oscillators has opened a path to energy efficient data processing. The success of this demonstration hinged on the intrinsic short-term memory of the oscillators. In this study, we extend the memory of the spin-torque nano-oscillators through time-delayed feedback. We leverage this extrinsic memory to increase the efficiency of solving pattern recognition tasks that require memory to discriminate different inputs. The large tunability of these non-linear oscillators allows us to control and optimize the delayed feedback memory using different operating conditions of applied current and magnetic field.
最近利用自旋扭矩纳米振荡器进行的神经形态计算演示为高效能数据处理开辟了一条道路。这一演示的成功取决于振荡器的固有短期记忆。在本研究中,我们通过延时反馈来扩展自旋扭矩纳米振荡器 的记忆。我们利用这种外部记忆来提高解决需要记忆以区分不同输入的模式识别任务的效率。这些非线性振荡器的高度可调性使我们能够使用施加电流和磁场的不同操作条件来控制和优化延迟反馈记忆。