Using Programmable Graphene Channels as Weights in Spin-Diffusive Neuromorphic Computing
Using Programmable Graphene Channels as Weights in Spin-Diffusive Neuromorphic Computing
复制标题
在自旋扩散神经形态计算中使用可编程石墨烯通道作为权重
DOI：
--
复制
发表时间：
2017
影响因子：
2.4
通讯作者：
S. Koester
中科院分区：
文献类型：
--
作者：
Jiaxi Hu;G. Stecklein;Y. Anugrah;P. Crowell;S. Koester
本文提出了一种基于石墨烯的自旋扩散神经网络，该网络利用了石墨烯的局部可调谐自旋输运和纳米磁体的非易失性。通过使用静电门控石墨烯作为自旋电子突触，可以在自旋域中执行加权求和操作，同时可以使用电荷域中的电路对权重进行编程。与磁动力学耦合的四分量自旋/电荷电路模拟用于显示神经元突触功能的可行性，并量化石墨烯在不同自旋弛豫机制下的模拟加权能力。这种使用基于石墨烯的突触设计的自旋扩散神经网络实现了每个单元 $cdot $ 突触 0.55–0.97 fJ 的总能耗，并且与数字网络相比，具有明显更好的可扩展性，特别是随着突触数量和位精度的增加。
A graphene-based spin-diffusive neural network is presented in this paper that takes advantage of the locally tunable spin transport of graphene and the non-volatility of nanomagnets. By using electrostatically gated graphene as spintronic synapses, a weighted summation operation can be performed in the spin domain while the weights can be programmed using circuits in the charge domain. Four-component spin/charge circuit simulations coupled to magnetic dynamics are used to show the feasibility of the neuron-synapse functionality and quantify the analog weighting capability of the graphene under different spin-relaxation mechanisms. This spin-diffusive neural network using a graphene-based synapse design achieves total energy consumption of 0.55–0.97 fJ per cell $cdot $ synapse and attains significantly better scalability compared to its digital counterparts, particularly as the number and bit accuracy of the synapses increases.
影响因子：
4
作者：
Balke, Benjamin;Fecher, Gerhard H.;Felser, Claudia
通讯作者：
Felser, Claudia