Purely Spintronic Perceptron with Unsupervised Learning Enabled by Four-Terminal Domain Wall-Magnetic Tunnel Junction Neuron

ORAL

Abstract

We propose a four-terminal domain wall-magnetic tunnel junction (DW-MTJ) neuron that enables the first-ever CMOS-free purely spintronic perceptron with unsupervised learning. The proposed leaky integrate-and-fire neuron has a ferromagnetic DW track coupled to a free layer of a binary MTJ by an electrically insulated layer. Current through the ferromagnetic track performs integration by moving the DW. Intrinsic leaking occurs by moving the DW in the opposite direction of integration due to either dipolar magnetic field, anisotropy gradient, or shape variation. When the DW passes underneath the electrically-isolated MTJ, it fires by switching between the anti-parallel resistive state and parallel conductive state. Additionally, by exploiting stray magnetic field interactions, these neurons perform lateral inhibition.
In a crossbar perceptron, the DW track of each four-terminal neuron is connected to the analog three-terminal DW-MTJ synapses. Finally, an unsupervised learning algorithm results from the feedback between the neuron MTJ and the third terminals of the analog synapses, providing best results of 98.11% accuracy on the Wisconsin breast cancer clustering task.

*This work was supported by the NSF under CCF Awards 1910800 and 1910997.

–

Presenters

  • Naimul Hassan

    • Electrical and Computer Engineering, University of Texas at Dallas

Authors

  • Naimul Hassan

    • Electrical and Computer Engineering, University of Texas at Dallas

  • Wesley Brigner

    • Electrical and Computer Engineering, University of Texas at Dallas
    • University of Texas at Dallas

  • Christopher H. Bennet

    • Sandia National Laboratories
    • Sandia National Laboratories, Albuquerque NM USA

  • Alvaro Velasquez

    • Air Force Research Laboratory

  • Xuan Hu

    • Electrical and Computer Engineering, University of Texas at Dallas
    • University of Texas at Dallas
    • Electrical & Computer Engineering, University of Texas at Dallas

  • Otitoaleke G. Akinola

    • Electrical and Computer Engineering, University of Texas at Austin
    • Electrical and Computer Engineering Dept., University of Texas at Austin, Austin TX USA

  • Can Cui

    • Electrical and Computer Engineering, University of Texas at Austin
    • ECE, The University of Texas at Austin
    • Electrical and Computer Engineering Dept., University of Texas at Austin, Austin TX USA

  • Felipe Garcia-Sanchez

    • Universidad de Salamanca
    • University of Salamanca
    • Applied Physics, Universidad de Salamanca
    • Department of Applied Physics, Universidad de Salamanca

  • Matthew J. Marinella

    • Sandia National Laboratories
    • Sandia National Laboratories, Albuquerque NM USA

  • Jean Anne C. Incorvia

    • Electrical and Computer Engineering, University of Texas at Austin
    • University of Texas at Austin
    • ECE, The University of Texas at Austin
    • Electrical and Computer Engineering Dept., University of Texas at Austin, Austin TX USA

  • Joseph S. Friedman

    • Electrical and Computer Engineering, University of Texas at Dallas
    • University of Texas at Dallas
    • Electrical and Computer Engineering Dept., University of Texas at Dallas, Richardson TX USA
    • Electrical & Computer Engineering, University of Texas at Dallas
    • Department of Electrical and Computer Engineering, University of Texas at Dallas