Researchers introduce Artificial Kuramoto Oscillatory Neurons (AKOrN), a dynamical alternative to traditional threshold units that synchronize neurons for competitive learning. The approach improves performance on tasks including unsupervised object discovery, adversarial robustness, uncertainty quantification, and reasoning by rethinking neural representation at the fundamental level.
Swormhörn is a custom synthesizer built with ESP32-S3 and pressure sensors that generates cicada sounds and simulates swarm behavior using the Kuramoto model, allowing performers to control synchronized swarm dynamics with accompanying LED feedback.