Autonomous Learning of Attractors for Neuromorphic Computing with Wien Bridge Oscillator Networks

TL;DR

This paper demonstrates a neuromorphic computing system using coupled Wien bridge oscillators that can learn and recall phase patterns autonomously through Hebbian adaptation, validated in both simulation and hardware.

Contribution

It introduces a novel oscillator network architecture that combines learning and inference in continuous dynamics, enabling autonomous pattern formation and energy landscape reshaping.

Findings

Learned phase patterns form stable attractors.

Hardware implementation confirms simulation results.

Network can adapt to inputs by reshaping its energy landscape.

Abstract

We present an oscillatory neuromorphic primitive implemented with networks of coupled Wien bridge oscillators and tunable resistive couplings. Phase relationships between oscillators encode patterns, and a local Hebbian learning rule continuously adapts the couplings, allowing learning and recall to emerge from the same ongoing analog dynamics rather than from separate training and inference phases. Using a Kuramoto-style phase model with an effective energy function, we show that learned phase patterns form attractor states and validate this behavior in simulation and hardware. We further realize a 2-4-2 architecture with a hidden layer of oscillators, whose bipartite visible-hidden coupling allows multiple internal configurations to produce the same visible phase states. When inputs are switched, transient spikes in energy followed by relaxation indicate how the network can reduce surprise by reshaping its energy landscape. These results support coupled oscillator circuits as a hardware platform for energy-based neuromorphic computing with autonomous, continuous learning.