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

TL;DR

This paper demonstrates a spintronic physical neural network that self-learns and adapts weights via intrinsic physical processes, enabling autonomous unsupervised learning with high scalability and efficiency.

Contribution

It introduces a magnetic texture-based Hopfield neural network that intrinsically performs gradient descent learning without external computation.

Findings

Physical spintronic system mimics Hopfield neural networks.

Conductance matrix evolves naturally under external voltage inputs.

Achieves high-similarity pattern associative memory.

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.