A self-learning magnetic Hopfield neural network with intrinsic gradient descent adaption

Abstract

Physical neural networks using physical materials and devices to mimic synapses and neurons offer an energy-efficient way to implement artificial neural networks. Yet, training physical neural networks are difficult and heavily relies on external computing resources. An emerging concept to solve this issue is called physical self-learning that uses intrinsic physical parameters as trainable weights. Under external inputs (i.e. training data), training is achieved by the natural evolution of physical parameters that intrinsically adapt modern learning rules via autonomous physical process, eliminating the requirements on external computation resources.Here, we demonstrate a real spintronic system that mimics Hopfield neural networks (HNN) and unsupervised learning is intrinsically performed via the evolution of physical process. Using magnetic texture defined conductance matrix as trainable weights, we illustrate that under external voltage inputs, the conductance matrix naturally evolves and adapts Oja's learning algorithm in a gradient descent manner. The self-learning HNN is scalable and can achieve associative memories on patterns with high similarities. The fast spin dynamics and reconfigurability of magnetic textures offer an advantageous platform towards efficient autonomous training directly in materials.

21 pages, 5 figures

References in corpus (20)

• Photonics for artificial intelligence and neuromorphic computing
• Deep physical neural networks enabled by a backpropagation algorithm for arbitrary physical systems
• Magnetic skyrmion artificial synapse for neuromorphic computing
• Vowel recognition with four coupled spin-torque nano-oscillators
• Learning without neurons in physical systems
• Hopfield Networks is All You Need
• Quantum materials for energy-efficient neuromorphic computing
• Enhancing associative memory recall and storage capacity using confocal cavity QED
• An atomic Boltzmann machine capable of on-chip learning
• Direct observation of a dynamical glass transition in a nanomagnetic artificial Hopfield network
• Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial
• Experimental quantum stochastic walks simulating associative memory of Hopfield neural networks
• Self-learning Machines based on Hamiltonian Echo Backpropagation
• Stochastic single flux quantum neuromorphic computing using magnetically tunable Josephson junctions
• Theory of magnetotransport in artificial kagome spin ice
• Learning by mistakes in memristor networks
• New Insights on Learning Rules for Hopfield Networks: Memory and Objective Function Minimisation
• Physical Neural Networks with Self-Learning Capabilities
• Network analysis of memristive device circuits: dynamics, stability and correlations
• Uncontrolled learning: co-design of neuromorphic hardware topology for neuromorphic algorithms