Spin-Transfer Torque Magnetic neuron for low power neuromorphic computing

Abhronil Sengupta, Kaushik Roy

Abstract

Neuromorphic computing attempts to emulate the remarkable efficiency of the human brain in vision, perception and cognition related tasks. Nanoscale devices that offer a direct mapping to the underlying neural computations have emerged as a promising candidate for such neuromorphic architectures. In this paper, a Magnetic Tunneling Junction (MTJ) has been proposed to perform the thresholding operation of a biological neuron. A crossbar array consisting of programmable resistive synapses generates an excitatory/inhibitory charge current input to the neuron. The magnetization of the free layer of the MTJ is manipulated by Spin-Transfer Torque generated by the net synaptic current. Algorithm, device and circuit co-simulation framework suggest the possibility of ~ 1.63 - 1.79x power savings in comparison to a 45nm digital CMOS implementation.
BibTeX
@inproceedings{sengupta2015spin,
  author = {Abhronil Sengupta and Kaushik Roy},
  title = {{Spin-Transfer Torque Magnetic neuron for low power neuromorphic computing}},
  booktitle = {IJCNN},
  year = {2015},
  doi = {10.1109/ijcnn.2015.7280306},
}

Loading related content...

Figure