An Empirical Study of the L2-Boost technique with Echo State Networks
This work addresses the parameter sensitivity problem in ESNs for time-series prediction, offering an incremental improvement over existing ensemble methods.
The study tackled the challenge of tuning Echo State Networks (ESNs) by applying the L2-Boost technique to ensembles of randomly initialized ESNs as weak predictors, achieving improved performance on five time-series benchmarks compared to a baseline averaging method.
A particular case of Recurrent Neural Network (RNN) was introduced at the beginning of the 2000s under the name of Echo State Networks (ESNs). The ESN model overcomes the limitations during the training of the RNNs while introducing no significant disadvantages. Although the model presents some well-identified drawbacks when the parameters are not well initialised. The performance of an ESN is highly dependent on its internal parameters and pattern of connectivity of the hidden-hidden weights Often, the tuning of the network parameters can be hard and can impact in the accuracy of the models. In this work, we investigate the performance of a specific boosting technique (called L2-Boost) with ESNs as single predictors. The L2-Boost technique has been shown to be an effective tool to combine "weak" predictors in regression problems. In this study, we use an ensemble of random initialized ESNs (without control their parameters) as "weak" predictors of the boosting procedure. We evaluate our approach on five well-know time-series benchmark problems. Additionally, we compare this technique with a baseline approach that consists of averaging the prediction of an ensemble of ESNs.