Phase Transition Adaptation
This work addresses improving computational efficiency in recurrent neural networks for researchers in machine learning, but it appears incremental as an extension of existing Reservoir Computing methods.
The paper tackles the problem of enhancing computational capacity in Reservoir Computing by introducing Phase Transition Adaptation, a local unsupervised learning mechanism that drives system dynamics to the 'edge of stability', and shows experimentally that this approach consistently achieves its purpose across several datasets.
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 paper, 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 behavior exhibited by the system elicits an enhancement in its overall computational capacity. We show experimentally that our approach consistently achieves its purpose over several datasets.