Magnetic domain wall neuron with intrinsic leaking and lateral inhibition capability

The challenge of developing an efficient artificial neuron is impeded by the use of external CMOS circuits to perform leaking and lateral inhibition. The proposed leaky integrate-and-fire neuron based on the three terminal magnetic tunnel junction (3T-MTJ) performs integration by pushing its domain wall (DW) with spin-transfer or spin-orbit torque. The leaking capability is achieved by pushing the neurons’ DWs in the direction opposite of integration using a stray field from a hard ferromagnet or a non-uniform energy landscape resulting from shape or anisotropy variation. Firing is performed by the MTJ stack. Finally, analog lateral inhibition is achieved by dipolar field repulsive coupling from each neuron. An integrating neuron thus pushes slower neighboring neurons’ DWs in the direction opposite of integration. Applying this lateral inhibition to a ten-neuron output layer within a neuromorphic crossbar structure enables the identification of handwritten digits with 94% accuracy.

[1]  C. Ross,et al.  Low Energy Magnetic Domain Wall Logic in Short, Narrow, Ferromagnetic Wires , 2012, IEEE Magnetics Letters.

[2]  Caroline A. Ross,et al.  A logic-in-memory design with 3-terminal magnetic tunnel junction function evaluators for convolutional neural networks , 2017, 2017 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[3]  Martin Stemmler,et al.  Power Consumption During Neuronal Computation , 2014, Proceedings of the IEEE.

[4]  Bernard Brezzo,et al.  TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip , 2015, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[5]  Jacques-Olivier Klein,et al.  Physical Realization of a Supervised Learning System Built with Organic Memristive Synapses , 2016, Scientific Reports.

[6]  C. A. Ross,et al.  Spintronic logic circuit and device prototypes utilizing domain walls in ferromagnetic wires with tunnel junction readout , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[7]  Joseph S. Friedman,et al.  Magnetic domain wall neuron with lateral inhibition , 2018, Journal of Applied Physics.

[8]  Jacques Gautrais,et al.  SpikeNET: A simulator for modeling large networks of integrate and fire neurons , 1999, Neurocomputing.

[9]  Mrigank Sharad,et al.  Energy-Efficient Non-Boolean Computing With Spin Neurons and Resistive Memory , 2014, IEEE Transactions on Nanotechnology.

[10]  Jacques-Olivier Klein,et al.  Bioinspired networks with nanoscale memristive devices that combine the unsupervised and supervised learning approaches , 2012, 2012 IEEE/ACM International Symposium on Nanoscale Architectures (NANOARCH).

[11]  Xing Chen,et al.  A compact skyrmionic leaky-integrate-fire spiking neuron device. , 2018, Nanoscale.

[12]  Christopher H. Bennett,et al.  Graded-Anisotropy-Induced Magnetic Domain Wall Drift for an Artificial Spintronic Leaky Integrate-and-Fire Neuron , 2019, IEEE Journal on Exploratory Solid-State Computational Devices and Circuits.

[13]  Andrew S. Cassidy,et al.  A million spiking-neuron integrated circuit with a scalable communication network and interface , 2014, Science.

[14]  Joseph S. Friedman,et al.  Shape-Based Magnetic Domain Wall Drift for an Artificial Spintronic Leaky Integrate-and-Fire Neuron , 2019, IEEE Transactions on Electron Devices.

[15]  Vijay Balasubramanian,et al.  Heterogeneity and Efficiency in the Brain , 2015, Proceedings of the IEEE.

[16]  Song Han,et al.  Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding , 2015, ICLR.

[17]  C. A. Ross,et al.  Logic circuit prototypes for three-terminal magnetic tunnel junctions with mobile domain walls , 2016, Nature Communications.