Research index
Gradient based hyperparameter optimization in Echo State Networks.
Thiede, Parlitz
Neural networks : the official journal of the International Neural Network Society1 Jul 2019
NobleIDark:/48914/w1/20260517/019F2653DOI10.1016/j.neunet.2019.02.001
Gradient based hyperparameter optimization in Echo State Networks.
Thiede, Parlitz · Neural networks : the official journal of the International Neural Network Society · 2019 · Subscription
NobleIDark:/48914/w1/20260517/019F2653DOI10.1016/j.neunet.2019.02.001
The full text is at the publisher
You can read the abstract here, or open it at the publisher.
Abstract
Like most machine learning algorithms, Echo State Networks possess several hyperparameters that have to be carefully tuned for achieving best performance. For minimizing the error on a specific task, we present a gradient based optimization algorithm, for the input scaling, the spectral radius, the leaking rate, and the regularization parameter.