Machine learning using magnetic stochastic synapses
Machine learning using magnetic stochastic synapses
复制标题
DOI：
10.1088/2634-4386/acdb96
复制
发表时间：
2023-03
期刊：
影响因子：
--
通讯作者：
Matthew O. A. Ellis;A. Welbourne;Stephan J. Kyle;P. Fry;D. Allwood;T. Hayward;E. Vasilaki
中科院分区：
文献类型：
--
作者：
Matthew O. A. Ellis;A. Welbourne;Stephan J. Kyle;P. Fry;D. Allwood;T. Hayward;E. Vasilaki
人工神经网络令人印象深刻的性能是以高能耗和二氧化碳排放为代价的。非传统的计算架构，磁系统作为候选者，有潜力作为替代能源高效的硬件，但仍然面临挑战，如随机行为，在实施。在这里，我们提出了一种方法，利用传统上有害的随机效应在纳米线的磁畴壁运动。我们展示了功能性二元随机突触以及梯度学习规则，该规则允许它们的训练适用于一系列随机系统。该规则，利用神经元输出分布的均值和方差，发现突触随机性和能量效率之间的权衡取决于每个突触的测量的数量。对于单次测量，该规则导致具有最小随机性的二进制突触，牺牲了鲁棒性的潜在性能。对于多次测量，突触分布是广泛的，近似于表现更好的连续突触。这种观察使我们能够根据所需的性能和设备的运行速度和能源成本来选择设计原则。我们在物理硬件上验证了性能，表明它与标准神经网络相当。
The impressive performance of artificial neural networks has come at the cost of high energy usage and CO2 emissions. Unconventional computing architectures, with magnetic systems as a candidate, have potential as alternative energy-efficient hardware, but, still face challenges, such as stochastic behaviour, in implementation. Here, we present a methodology for exploiting the traditionally detrimental stochastic effects in magnetic domain-wall motion in nanowires. We demonstrate functional binary stochastic synapses alongside a gradient learning rule that allows their training with applicability to a range of stochastic systems. The rule, utilising the mean and variance of the neuronal output distribution, finds a trade-off between synaptic stochasticity and energy efficiency depending on the number of measurements of each synapse. For single measurements, the rule results in binary synapses with minimal stochasticity, sacrificing potential performance for robustness. For multiple measurements, synaptic distributions are broad, approximating better-performing continuous synapses. This observation allows us to choose design principles depending on the desired performance and the device’s operational speed and energy cost. We verify performance on physical hardware, showing it is comparable to a standard neural network.