近日,北师大袁喆团队在国际知名期刊《Physical Review Applied》上发表题为“Anticipative Tracking with the Short-Term Synaptic Plasticity of Spintronic Devices”的文章,他们通过微磁学模拟证明,基于磁性隧 ...
文章链接:https://journals.aps.org/prapplied/abstract/10.1103/PhysRevApplied.14.044060 图1. 连续吸引子神经网络 背景 使用人工神经网络进行的计算在模式识别和自然语言编程等应用中显示出了极大的效率。这些计算通常需要有限的处理时间,因此给那些有时间限制的任务带来了挑战,例如,跟踪快速移动的对象。用相关滤波和人工神经网络等多种算法进行了目标跟踪。视觉目标跟踪是动物和人类的一项基本认知能力。一些特殊的机制在生物大脑中被固有地采用,以补偿神经系统有限的处理时间。一种生物启发算法被开发,以纳入延迟补偿到跟踪方案,并允许它预测快速移动的目标。它是基于一种特殊的神经网络——连续吸引子神经网络(CANN)实现的,这种神经网络已经在动物大脑中进行了实验观察。使用短期抑制(STD)的神经突触效能,神经元的尖峰频率适应,或来自邻近层的负反馈的CANNs可以实现预期的跟踪 摘要 在现有的人工智能技术中,对认知任务中的高速对象进行实时跟踪具有很大的挑战性,因为数据处理和计算都很耗时,会造成严重的时间延迟。摘要脑激发连续吸引子神经网络(CANN)可用于追踪快速移动的目标,如果网络中的动态突触具有短期可塑性,则其时滞得到了内在补偿。在这里,我们展示了具有短期抑制的突触可以通过磁隧道结实现,这在一个广泛应用的数学模型中完美地再现了突触权重的动力学。然后,这些动态突触被整合到一维和二维CANNs中,这些CANNs被证明具有通过微磁模拟来预测移动物体的能力。这种基于自旋电子学的便携式神经形态计算硬件无需训练,因此在运动目标跟踪技术中非常有前途。 Real-time tracking ofhigh-speed objects in cognitive tasks is challenging in the present artificial intelligence techniques because the data processing and computation are time consuming, resulting in impeditive time delays. A brain-inspired continuous attractor neural network (CANN) can be used to track fast moving targets, where the time delays are intrinsically compensated if the dynamical synapses in the network have short-term plasticity. Here, we show that synapses with short-term depression can be realized by a magnetic tunnel junction, which perfectly reproduces the dynamics of the synaptic weight in a widely applied mathematical model. Then, these dynamical synapses are incorporated into one-dimensional and two-dimensional CANNs, which are demonstrated to have the ability to predict a moving object via micromagnetic simulations. This portable spintronics-based hardware for neuromorphic computing needs no training and is therefore very promising for the tracking technology of moving targets. |