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
Using Programmable Graphene Channels as Weights in Spin-Diffusive Neuromorphic Computing
摘要：
基于石墨烯的自旋扩散（GrSD）的神经网络，在这项工作中，利用本地可调的自旋输运的石墨烯和纳米磁体的非挥发性。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。耦合到磁动力学的四分量自旋/电荷电路模拟用于显示神经元突触功能的可行性，并量化不同自旋弛豫机制下石墨烯的模拟加权能力。通过实现无晶体管权重实现，石墨烯自旋扩散神经网络将每个细胞突触的能耗降低到0.08-0.32 fJ，并且与其数字对应物相比实现了显著更好的可扩展性，特别是随着突触的数量和位精度的增加。
英文摘要：
A graphene-based spin-diffusive (GrSD) neural network is presented in this work 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. By realizing transistor-free weight implementation, the graphene spin-diffusive neural network reduces the energy consumption to 0.08-0.32 fJ per cell-synapse and achieves significantly better scalability compared to its digital counterparts, particularly as the number and bit accuracy of the synapses increases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
