Maximized lateral inhibition in paired magnetic domain wall racetracks for neuromorphic computing

Cui, Can; Akinola, Otitoaleke G.; Hassan, Naimul; Bennett, Christopher H.; Marinella, Matthew J.; Friedman, Joseph S.; Incorvia, Jean Anne C.

doi:10.1088/1361-6528/ab86e8

Maximized lateral inhibition in paired magnetic domain wall racetracks for neuromorphic computing

Journal Article · Wed Apr 29 00:00:00 EDT 2020 · Nanotechnology

DOI:https://doi.org/10.1088/1361-6528/ab86e8· OSTI ID:1614786

Cui, Can ^[1]; ^[1]; Hassan, Naimul ^[2]; ^[3]; Marinella, Matthew J. ^[3]; Friedman, Joseph S. ^[2]; ^[1]

Univ. of Texas, Austin, TX (United States)
Univ. of Texas at Dallas, Richardson, TX (United States)
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

Lateral inhibition is an important functionality in neuromorphic computing, modeled after the biological neuron behavior that a firing neuron deactivates its neighbors belonging to the same layer and prevents them from firing. In most neuromorphic hardware platforms lateral inhibition is implemented by external circuitry, thereby decreasing the energy efficiency and increasing the area overhead of such systems. Recently, the domain wall—magnetic tunnel junction (DW-MTJ) artificial neuron is demonstrated in modeling to be intrinsically inhibitory. Without peripheral circuitry, lateral inhibition in DW-MTJ neurons results from magnetostatic interaction between neighboring neuron cells. However, the lateral inhibition mechanism in DW-MTJ neurons has not been studied thoroughly, leading to weak inhibition only in very closely-spaced devices. This work approaches these problems by modeling current- and field- driven DW motion in a pair of adjacent DW-MTJ neurons. We maximize the magnitude of lateral inhibition by tuning the magnetic interaction between the neurons. The results are explained by current-driven DW velocity characteristics in response to an external magnetic field and quantified by an analytical model. Dependence of lateral inhibition strength on device parameters is also studied. Finally, lateral inhibition behavior in an array of 1000 DW-MTJ neurons is demonstrated. Our results provide a guideline for the optimization of lateral inhibition implementation in DW-MTJ neurons. Finally, with strong lateral inhibition achieved, a path towards competitive learning algorithms such as the winner-take-all are made possible on such neuromorphic devices.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC04-94AL85000; NA0003525

OSTI ID:: 1614786

Alternate ID(s):: OSTI ID: 1617248
OSTI ID: 23114754

Report Number(s):: SAND--2020-3552J; 684999

Journal Information:: Nanotechnology, Journal Name: Nanotechnology Journal Issue: 29 Vol. 31; ISSN 0957-4484

Publisher:: IOP PublishingCopyright Statement

Country of Publication:: United States

Language:: English

References (31)

A silicon model of early visual processing Mead, Carver A.; Mahowald, M. A. Neural Networks, Vol. 1, Issue 1 https://doi.org/10.1016/0893-6080(88)90024-X	journal	January 1988
Competitive learning algorithms for vector quantization Ahalt, Stanley C.; Krishnamurthy, Ashok K.; Chen, Prakoon Neural Networks, Vol. 3, Issue 3 https://doi.org/10.1016/0893-6080(90)90071-R	journal	January 1990
Dynamics of a Winner-Take-All Neural Network Fang, Yuguang; Cohen, Michael A.; Kincaid, Thomas G. Neural Networks, Vol. 9, Issue 7 https://doi.org/10.1016/0893-6080(96)00019-6	journal	October 1996
A Theoretical Analysis of Neuronal Variability Stein, Richard B. Biophysical Journal, Vol. 5, Issue 2 https://doi.org/10.1016/S0006-3495(65)86709-1	journal	March 1965
Logic circuit prototypes for three-terminal magnetic tunnel junctions with mobile domain walls Currivan-Incorvia, J. A.; Siddiqui, S.; Dutta, S. Nature Communications, Vol. 7, Issue 1 https://doi.org/10.1038/ncomms10275	journal	January 2016
The motion of 180° domain walls in uniform dc magnetic fields Schryer, N. L.; Walker, L. R. Journal of Applied Physics, Vol. 45, Issue 12 https://doi.org/10.1063/1.1663252	journal	December 1974
Calculation of the magnetic stray field of a uniaxial magnetic domain Engel-Herbert, R.; Hesjedal, T. Journal of Applied Physics, Vol. 97, Issue 7 https://doi.org/10.1063/1.1883308	journal	April 2005
Current-induced domain wall motion in a nanowire with perpendicular magnetic anisotropy Jung, Soon-Wook; Kim, Woojin; Lee, Taek-Dong Applied Physics Letters, Vol. 92, Issue 20 https://doi.org/10.1063/1.2926664	journal	May 2008
The design and verification of MuMax3 Vansteenkiste, Arne; Leliaert, Jonathan; Dvornik, Mykola AIP Advances, Vol. 4, Issue 10 https://doi.org/10.1063/1.4899186	journal	October 2014
Magnetic domain wall neuron with lateral inhibition Hassan, Naimul; Hu, Xuan; Jiang-Wei, Lucian Journal of Applied Physics, Vol. 124, Issue 15 https://doi.org/10.1063/1.5042452	journal	October 2018
Large-scale neuromorphic computing systems Furber, Steve Journal of Neural Engineering, Vol. 13, Issue 5 https://doi.org/10.1088/1741-2560/13/5/051001	journal	August 2016
A high-precision VLSI winner-take-all circuit for self-organizing neural networks Choi, J.; Sheu, B. J. IEEE Journal of Solid-State Circuits, Vol. 28, Issue 5 https://doi.org/10.1109/4.229397	journal	May 1993
K-winners-take-all circuit with O(N) complexity Urahama, K.; Nagao, T. IEEE Transactions on Neural Networks, Vol. 6, Issue 3 https://doi.org/10.1109/72.377986	journal	May 1995
Multi-column deep neural networks for image classification Ciresan, D.; Meier, U.; Schmidhuber, J. 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2012.6248110	conference	June 2012
Character Recognition using Spiking Neural Networks Gupta, Ankur; Long, Lyle N. 2007 International Joint Conference on Neural Networks https://doi.org/10.1109/IJCNN.2007.4370930	conference	August 2007
Hebbian learning with winner take all for spiking neural networks Gupta, Ankur; Long, Lyle N. 2009 International Joint Conference on Neural Networks (IJCNN 2009 - Atlanta) https://doi.org/10.1109/IJCNN.2009.5178751	conference	June 2009
CMOS and Memristor-Based Neural Network Design for Position Detection Ebong, Idongesit E.; Mazumder, Pinaki Proceedings of the IEEE, Vol. 100, Issue 6 https://doi.org/10.1109/JPROC.2011.2173089	journal	June 2012
Graded-Anisotropy-Induced Magnetic Domain Wall Drift for an Artificial Spintronic Leaky Integrate-and-Fire Neuron Brigner, Wesley H.; Hu, Xuan; Hassan, Naimul IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, Vol. 5, Issue 1 https://doi.org/10.1109/JXCDC.2019.2904191	journal	June 2019
Domain Structure in CoFeB Thin Films With Perpendicular Magnetic Anisotropy Yamanouchi, Michihiko; Jander, Albrecht; Dhagat, Pallavi IEEE Magnetics Letters, Vol. 2 https://doi.org/10.1109/LMAG.2011.2159484	journal	January 2011
Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets Sengupta, Abhronil; Shim, Yong; Roy, Kaushik IEEE Transactions on Biomedical Circuits and Systems, Vol. 10, Issue 6 https://doi.org/10.1109/TBCAS.2016.2525823	journal	December 2016
Incorporating Data Flow Ideas into von Neumann Processors for Parallel Execution Buehrer, Richard; Ekanadham, Kattamuri IEEE Transactions on Computers, Vol. C-36, Issue 12 https://doi.org/10.1109/TC.1987.5009501	journal	December 1987
Shape-Based Magnetic Domain Wall Drift for an Artificial Spintronic Leaky Integrate-and-Fire Neuron Brigner, Wesley H.; Friedman, Joseph S.; Hassan, Naimul IEEE Transactions on Electron Devices, Vol. 66, Issue 11 https://doi.org/10.1109/TED.2019.2938952	journal	November 2019
Spin-Based Neuron Model With Domain-Wall Magnets as Synapse Sharad, M.; Augustine, C.; Panagopoulos, G. IEEE Transactions on Nanotechnology, Vol. 11, Issue 4 https://doi.org/10.1109/TNANO.2012.2202125	journal	July 2012
Simple model of spiking neurons Izhikevich, E. M. IEEE Transactions on Neural Networks, Vol. 14, Issue 6 https://doi.org/10.1109/TNN.2003.820440	journal	November 2003
Vector-Matrix Multiply and Winner-Take-All as an Analog Classifier Ramakrishnan, Shubha; Hasler, Jennifer IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Vol. 22, Issue 2 https://doi.org/10.1109/TVLSI.2013.2245351	journal	February 2014
A million spiking-neuron integrated circuit with a scalable communication network and interface Merolla, P. A.; Arthur, J. V.; Alvarez-Icaza, R. Science, Vol. 345, Issue 6197 https://doi.org/10.1126/science.1254642	journal	August 2014
Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware Blouw, Peter; Choo, Xuan; Hunsberger, Eric Proceedings of the 7th Annual Neuro-inspired Computational Elements Workshop on - NICE '19 https://doi.org/10.1145/3320288.3320304	conference	January 2019
Can programming be liberated from the von Neumann style?: a functional style and its algebra of programs Backus, John Communications of the ACM, Vol. 21, Issue 8 https://doi.org/10.1145/359576.359579	journal	August 1978
Adaptive Exponential Integrate-and-Fire Model as an Effective Description of Neuronal Activity Brette, Romain; Gerstner, Wulfram Journal of Neurophysiology, Vol. 94, Issue 5 https://doi.org/10.1152/jn.00686.2005	journal	November 2005
On the Computational Power of Winner-Take-All Maass, Wolfgang Neural Computation, Vol. 12, Issue 11 https://doi.org/10.1162/089976600300014827	journal	November 2000
Domain wall mobility, stability and Walker breakdown in magnetic nanowires Mougin, A.; Cormier, M.; Adam, J. P. Europhysics Letters (EPL), Vol. 78, Issue 5 https://doi.org/10.1209/0295-5075/78/57007	journal	May 2007

Cited By (1)

Controllable Reset Behavior in Domain Wall–Magnetic Tunnel Junction Artificial Neurons for Task-Adaptable Computation Liu, Samuel; Bennett, Christopher; Friedman, Joseph IEEE Magnetics Letters, Vol. 12 https://doi.org/10.1109/lmag.2021.3069666	journal	January 2021

Similar Records

Shape Anisotropy-Dependent Leaking in Magnetic Neurons for Bio-Mimetic Neuromorphic Computing

Journal Article · Mon Jan 13 23:00:00 EST 2025 · ACS Nano · OSTI ID:2505114

Controllable Reset Behavior in Domain Wall–Magnetic Tunnel Junction Artificial Neurons for Task-Adaptable Computation

Journal Article · Tue Mar 30 00:00:00 EDT 2021 · IEEE Magnetics Letters · OSTI ID:1782562

Three Artificial Spintronic Leaky Integrate-and-Fire Neurons

Journal Article · Thu Jun 25 00:00:00 EDT 2020 · SPIN · OSTI ID:1618070

Related Subjects

77 NANOSCIENCE AND NANOTECHNOLOGY
97 MATHEMATICS AND COMPUTING
domain wall motion
lateral inhibition
neuromorphic computing
spin transfer torque
winner-take-all

Maximized lateral inhibition in paired magnetic domain wall racetracks for neuromorphic computing

Citation Formats

References (31)

Cited By (1)

Similar Records

Related Subjects