A robust autoassociative memory with coupled networks of Kuramoto-type oscillators
This work addresses limitations in oscillatory neural networks for pattern recognition, offering a more robust and scalable solution, though it appears incremental in improving existing methods.
The paper tackled the problem of uncertain recognition success and unfavorable scaling in oscillatory neural networks for pattern recognition by proposing a new network architecture of coupled oscillators, which eliminates these issues and demonstrates isolated attractors as output patterns with derived criteria for recognition success.
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.