Reservoir regularization stabilizes learning of Echo State Networks with output feedback
Felix Reinhart, Jochen J. Steil · 2011
Abstract. Output feedback is crucial for autonomous and parameterized pattern generation with reservoir networks. Read-out learning can lead to error amplification in these settings and therefore regularization is important for both generalization and reduction of error amplification. We show that regularization of the inner reservoir network mitigates parameter dependencies and boosts the task-specific performance. 1