Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets

Abstract

Non-Boolean computing based on emerging post-CMOS technologies can potentially pave the way for low-power neural computing platforms. However, existing work on such emerging neuromorphic architectures have either focused on solely mimicking the neuron, or the synapse functionality. While memristive devices have been proposed to emulate biological synapses, spintronic devices have proved to be efficient at performing the thresholding operation of the neuron at ultra-low currents. In this work, we propose an All-Spin Artificial Neural Network where a single spintronic device acts as the basic building block of the system. The device offers a direct mapping to synapse and neuron functionalities in the brain while inter-layer network communication is accomplished via CMOS transistors. To the best of our knowledge, this is the first demonstration of a neural architecture where a single nanoelectronic device is able to mimic both neurons and synapses. The ultra-low voltage operation of low resistance magneto-metallic neurons enables the low-voltage operation of the array of spintronic synapses, thereby leading to ultra-low power neural architectures. Device-level simulations, calibrated to experimental results, was used to drive the circuit and system level simulations of the neural network for a standard pattern recognition problem. Simulation studies indicate energy savings by ~ 100x in comparison to a corresponding digital/ analog CMOS neuron implementation.

The article will appear in a future issue of IEEE Transactions on Biomedical Circuits and Systems

References in corpus (7)

• Deep Learning in Neural Networks: An Overview
• Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors
• Roadmap for Emerging Materials for Spintronic Device Applications
• Spin-Based Neuron Model with Domain Wall Magnets as Synapse
• Spin-Orbit Torque Induced Spike-Timing Dependent Plasticity
• Spin Orbit Torque Based Electronic Neuron
• Deterministic Domain Wall Motion Orthogonal To Current Flow Due To Spin Orbit Torque

Cited by in corpus (40)

• Stochastic p-bits for Invertible Logic
• Magnetic domain wall based synaptic and activation function generator for neuromorphic accelerators
• Exploring the Connection Between Binary and Spiking Neural Networks
• Low Barrier Nanomagnets as p-bits for Spin Logic
• Straintronics: Manipulating the Magnetization of Magnetostrictive Nanomagnets with Strain for Energy-Efficient Applications
• Technology Aware Training in Memristive Neuromorphic Systems based on non-ideal Synaptic Crossbars
• On-chip learning for domain wall synapse based Fully Connected Neural Network
• Shape-based Magnetic Domain Wall Drift for an Artificial Spintronic Leaky Integrate-and-Fire Neuron
• Domain Wall-Magnetic Tunnel Junction Spin Orbit Torque Devices and Circuits for In-Memory Computing
• Quantifying power use in silicon photonic neural networks
• Bilayer-skyrmion-based design of neuron and synapse for spiking neural network
• Energy-efficient switching of nanomagnets for computing: Straintronics and other methodologies
• All-Spin Bayesian Neural Networks
• TraNNsformer: Neural network transformation for memristive crossbar based neuromorphic system design
• Emerging spintronics phenomena and applications
• Energy Efficient Learning with Low Resolution Stochastic Domain Wall Synapse Based Deep Neural Networks
• Intrinsic synaptic plasticity of ferroelectric field effect transistors for online learning
• PUMA: A Programmable Ultra-efficient Memristor-based Accelerator for Machine Learning Inference
• Crystal Structure, Magnetism, and Electronic Properties of New Rare-Earth-Free Ferromagnetic MnPt5As
• Voltage control of domain walls in magnetic nanowires for energy efficient neuromorphic devices
• Stochastic Domain Wall-Magnetic Tunnel Junction Artificial Neurons for Noise-Resilient Spiking Neural Networks
• X-CHANGR: Changing Memristive Crossbar Mapping for Mitigating Line-Resistance Induced Accuracy Degradation in Deep Neural Networks
• Applications of Nanomagnets as Dynamical Systems
• Controllable reset behavior in domain wall-magnetic tunnel junction artificial neurons for task-adaptable computation
• Design of a Low Voltage Analog-to-Digital Converter using Voltage Controlled Stochastic Switching of Low Barrier Nanomagnets
• Stochastic Magnetoelectric Neuron for Temporal Information Encoding
• Mimicking synaptic plasticity with wedged Pt/Co/Pt spin-orbit torque device
• Photonic kernel machine learning for ultrafast spectral analysis
• Current-Induced Dynamics of Chiral Magnetic Structures: Creation, Motion, and Applications
• RESPARC: A Reconfigurable and Energy-Efficient Architecture with Memristive Crossbars for Deep Spiking Neural Networks
• Efficiency-driven Hardware Optimization for Adversarially Robust Neural Networks
• SwitchX: Gmin-Gmax Switching for Energy-Efficient and Robust Implementation of Binary Neural Networks on ReRAM Xbars
• A Non-Volatile All-Spin Non-Binary Matrix Multiplier: An Efficient Hardware Accelerator for Machine Learning
• Quantized Non-Volatile Nanomagnetic Synapse based Autoencoder for Efficient Unsupervised Network Anomaly Detection
• Ultra-low Power Domain Wall Device for Spin-based Neuromorphic Computing
• CMOS-Free Multilayer Perceptron Enabled by Four-Terminal MTJ Device
• Facilitating domain wall injection in magnetic nanowires by electrical means
• Hybrid Piezoelectric-Magnetic Neurons: A Proposal for Energy-Efficient Machine Learning
• Unsupervised Competitive Hardware Learning Rule for Spintronic Clustering Architecture
• Domain Wall Leaky Integrate-and-Fire Neurons with Shape-Based Configurable Activation Functions