Shape-Dependent Multi-Weight Magnetic Artificial Synapses for Neuromorphic Computing

In neuromorphic computing, artificial synapses provide a multi-weight conductance state that is set based on inputs from neurons, analogous to the brain. Additional properties of the synapse beyond multiple weights can be needed, and can depend on the application, requiring the need for generating different synapse behaviors from the same materials. Here, we measure artificial synapses based on magnetic materials that use a magnetic tunnel junction and a magnetic domain wall. By fabricating lithographic notches in a domain wall track underneath a single magnetic tunnel junction, we achieve 4-5 stable resistance states that can be repeatably controlled electrically using spin orbit torque. We analyze the effect of geometry on the synapse behavior, showing that a trapezoidal device has asymmetric weight updates with high controllability, while a straight device has higher stochasticity, but with stable resistance levels. The device data is input into neuromorphic computing simulators to show the usefulness of application-specific synaptic functions. Implementing an artificial neural network applied on streamed Fashion-MNIST data, we show that the trapezoidal magnetic synapse can be used as a metaplastic function for efficient online learning. Implementing a convolutional neural network for CIFAR-100 image recognition, we show that the straight magnetic synapse achieves near-ideal inference accuracy, due to the stability of its resistance levels. This work shows multi-weight magnetic synapses are a feasible technology for neuromorphic computing and provides design guidelines for emerging artificial synapse technologies.

[1]  Kaushik Roy,et al.  Magnetic Tunnel Junction Mimics Stochastic Cortical Spiking Neurons , 2015, Scientific Reports.

[2]  Shimeng Yu,et al.  Ferroelectric FET analog synapse for acceleration of deep neural network training , 2017, 2017 IEEE International Electron Devices Meeting (IEDM).

[3]  Supriyo Datta,et al.  Intrinsic optimization using stochastic nanomagnets , 2016, Scientific Reports.

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

[5]  M. Marinella,et al.  In situ Parallel Training of Analog Neural Network Using Electrochemical Random-Access Memory , 2021, Frontiers in Neuroscience.

[6]  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.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Peng Huang,et al.  Optimized learning scheme for grayscale image recognition in a RRAM based analog neuromorphic system , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[10]  Roland Vollgraf,et al.  Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms , 2017, ArXiv.

[11]  Kaushik Roy,et al.  Stochastic Spin-Orbit Torque Devices as Elements for Bayesian Inference , 2017, Scientific Reports.

[12]  Jacques-Olivier Klein,et al.  Spin-Transfer Torque Magnetic Memory as a Stochastic Memristive Synapse for Neuromorphic Systems , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[13]  Xiaoyu Sun,et al.  Impact of Non-Ideal Characteristics of Resistive Synaptic Devices on Implementing Convolutional Neural Networks , 2019, IEEE Journal on Emerging and Selected Topics in Circuits and Systems.

[14]  Damien Querlioz,et al.  Bioinspired Programming of Memory Devices for Implementing an Inference Engine , 2015, Proceedings of the IEEE.

[15]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[16]  D. Henze,et al.  The multifarious hippocampal mossy fiber pathway: a review , 2000, Neuroscience.

[17]  P. Jonas,et al.  Efficacy and Stability of Quantal GABA Release at a Hippocampal Interneuron–Principal Neuron Synapse , 2000, The Journal of Neuroscience.

[18]  A. Salleo,et al.  Temperature-resilient solid-state organic artificial synapses for neuromorphic computing , 2020, Science Advances.

[19]  Steven J. Plimpton,et al.  Achieving ideal accuracies in analog neuromorphic computing using periodic carry , 2017, 2017 Symposium on VLSI Technology.

[20]  Matthew J. Marinella,et al.  Using Floating-Gate Memory to Train Ideal Accuracy Neural Networks , 2019, IEEE Journal on Exploratory Solid-State Computational Devices and Circuits.

[21]  Kaushik Roy,et al.  Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets , 2015, IEEE Transactions on Biomedical Circuits and Systems.

[22]  Damien Querlioz,et al.  Narrow Heater Bottom Electrode‐Based Phase Change Memory as a Bidirectional Artificial Synapse , 2018, Advanced Electronic Materials.

[23]  Jozsef Csicsvari,et al.  Hippocampal Reactivation of Random Trajectories Resembling Brownian Diffusion , 2019, Neuron.

[24]  A review , 2019 .

[25]  Damien Querlioz,et al.  Synaptic metaplasticity in binarized neural networks , 2020, Nature Communications.

[26]  Mahendra Pakala,et al.  Process Optimization of Perpendicular Magnetic Tunnel Junction Arrays for Last-Level Cache beyond 7 nm Node , 2018, 2018 IEEE Symposium on VLSI Technology.

[27]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Dharmendra S. Modha,et al.  Deep neural networks are robust to weight binarization and other non-linear distortions , 2016, ArXiv.

[29]  Wolfgang Maass,et al.  Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons , 2011, PLoS Comput. Biol..

[30]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[31]  D. Mocuta,et al.  Spin-torque-driven MTJs with extended free layer for logic applications , 2018, Journal of Physics D: Applied Physics.

[32]  Shimeng Yu,et al.  A Methodology to Improve Linearity of Analog RRAM for Neuromorphic Computing , 2018, 2018 IEEE Symposium on VLSI Technology.

[33]  Sang-Hyuk Lee,et al.  Asymmetric ground state spin configuration of transverse domain wall on symmetrically notched ferromagnetic nanowires , 2010 .

[34]  Matthew J. Marinella,et al.  Wafer-Scale TaOx Device Variability and Implications for Neuromorphic Computing Applications , 2019, 2019 IEEE International Reliability Physics Symposium (IRPS).

[35]  Martin Fränzl,et al.  Active particle feedback control with a single-shot detection convolutional neural network , 2020, Scientific Reports.

[36]  Controllable Reset Behavior in Domain Wall–Magnetic Tunnel Junction Artificial Neurons for Task-Adaptable Computation , 2021, IEEE Magnetics Letters.

[37]  Sumit Dutta,et al.  Magnetic domain wall based synaptic and activation function generator for neuromorphic accelerators , 2019, Nano letters.

[38]  Christopher H. Bennett,et al.  Maximized lateral inhibition in paired magnetic domain wall racetracks for neuromorphic computing , 2019, Nanotechnology.

[39]  Kaushik Roy,et al.  Magnetic Tunnel Junction Based Long-Term Short-Term Stochastic Synapse for a Spiking Neural Network with On-Chip STDP Learning , 2016, Scientific Reports.

[40]  Byoung Hun Lee,et al.  Nanoscale RRAM-based synaptic electronics: toward a neuromorphic computing device , 2013, Nanotechnology.

[41]  P. Laczkowski,et al.  Elementary depinning processes of magnetic domain walls under fields and currents , 2014, Scientific Reports.