• echo state networks
• edge of stability
• machine learning
• recurrent neural networks
• reservoir computing
• unsupervised adaptation

Artificial recurrent neural networks are a powerful information processing abstraction, and Reservoir Computing provides an efficient strategy to build robust implementations by projecting external inputs into high dimensional dynamical system trajectories. In this contribution, we propose an extension of the original approach, a local unsupervised learning mechanism we call Phase Transition Adaptation, designed to drive the system dynamics towards the 'edge of stability'. Here, the complex behaviour exhibited by the system should elicit an enhancement in its overall computational capacity. We show experimentally that our approach consistently achieves its purpose over several datasets.