Spin-Based Neuron Model with Domain Wall Magnets as Synapse

Abstract

We present artificial neural network design using spin devices that achieves ultra low voltage operation, low power consumption, high speed, and high integration density. We employ spin torque switched nano-magnets for modelling neuron and domain wall magnets for compact, programmable synapses. The spin based neuron-synapse units operate locally at ultra low supply voltage of 30mV resulting in low computation power. CMOS based inter-neuron communication is employed to realize network-level functionality. We corroborate circuit operation with physics based models developed for the spin devices. Simulation results for character recognition as a benchmark application shows 95% lower power consumption as compared to 45nm CMOS design.

References in corpus (5)

• Non-collinear Magnetoelectronics
• Velocity of domain-wall motion induced by electrical current in a ferromagnetic semiconductor (Ga,Mn)As
• Proposal of a spin torque majority gate logic
• Switching energy-delay of all-spin logic devices
• All Spin Logic device with inbuilt Non-Reciprocity

Cited by in corpus (34)

• Spin torque building blocks
• Filamentary Switching: Synaptic Plasticity through Device Volatility
• Proposal for an All-Spin Artificial Neural Network: Emulating Neural and Synaptic Functionalities Through Domain Wall Motion in Ferromagnets
• Magnetic Skyrmions for Unconventional Computing
• Magnetic domain wall based synaptic and activation function generator for neuromorphic accelerators
• Probabilistic Deep Spiking Neural Systems Enabled by Magnetic Tunnel Junction
• Hybrid Spintronic-CMOS Spiking Neural Network With On-Chip Learning: Devices, Circuits and Systems
• Spin Orbit Torque Based Electronic Neuron
• Straintronics: Manipulating the Magnetization of Magnetostrictive Nanomagnets with Strain for Energy-Efficient Applications
• Quantum materials for energy-efficient neuromorphic computing
• STT-SNN: A Spin-Transfer-Torque Based Soft-Limiting Non-Linear Neuron for Low-Power Artificial Neural Networks
• Spin Neurons: A Possible Path to Energy-Efficient Neuromorphic Computers
• Proposal For Neuromorphic Hardware Using Spin Devices
• Energy-efficient switching of nanomagnets for computing: Straintronics and other methodologies
• Boolean and Non-Boolean Computation With Spin Devices
• Neuromorphic weighted sums with magnetic skyrmions
• Emerging spintronics phenomena and applications
• Ultra Low Energy Analog Image Processing Using Spin Neurons
• Voltage control of domain walls in magnetic nanowires for energy efficient neuromorphic devices
• Controllable reset behavior in domain wall-magnetic tunnel junction artificial neurons for task-adaptable computation
• Control and tunability of magnetic bubble states in multilayers with strong perpendicular magnetic anisotropy at ambient conditions
• Evaluating Spintronic Devices Using The Modular Approach
• Analog Signal Processing Using Stochastic Magnets
• Helitronics for classical and unconventional computing
• Current-Induced Dynamics of Chiral Magnetic Structures: Creation, Motion, and Applications
• Spin-Orbit-Torque-based Devices, Circuits and Architectures
• Smart Detector Cell: A Scalable All-Spin Circuit for Low Power Non-Boolean Pattern Recognition
• Voltage-induced high-speed DW motion in a synthetic antiferromagnet
• Domain wall displacement by remote spin-current injection
• Hybrid Piezoelectric-Magnetic Neurons: A Proposal for Energy-Efficient Machine Learning
• Facilitating domain wall injection in magnetic nanowires by electrical means
• Spintronics for neuromorphic computing
• Transverse domain walls in thin ferromagnetic strips
• Learning Spike time codes through Morphological Learning with Binary Synapses