A robust autoassociative memory with coupled networks of Kuramoto-type oscillators

TL;DR

This paper introduces a new coupled oscillator network architecture for pattern recognition that overcomes scalability and complexity issues of existing systems, supported by simulations and analytical insights.

Contribution

The paper presents a novel oscillator network design with isolated attractors for robust pattern recognition, avoiding previous limitations.

Findings

Network exhibits stable isolated attractors for patterns

Recognition success criteria derived from basin of attraction analysis

Simulation results demonstrate effective pattern recognition

Abstract

Uncertain recognition success, unfavorable scaling of connection complexity or dependence on complex external input impair the usefulness of current oscillatory neural networks for pattern recognition or restrict technical realizations to small networks. We propose a new network architecture of coupled oscillators for pattern recognition which shows none of the mentioned aws. Furthermore we illustrate the recognition process with simulation results and analyze the new dynamics analytically: Possible output patterns are isolated attractors of the system. Additionally, simple criteria for recognition success are derived from a lower bound on the basins of attraction.