Deep Residual Echo State Networks: exploring residual orthogonal connections in untrained Recurrent Neural Networks
This work addresses a specific bottleneck in reservoir computing for time series analysis, offering an incremental improvement over existing methods.
The paper tackled the problem of long-term information processing in Echo State Networks by introducing Deep Residual Echo State Networks with orthogonal residual connections, resulting in significant boosts in memory capacity and long-term temporal modeling as shown in experiments on various time series tasks.
Echo State Networks (ESNs) are a particular type of untrained Recurrent Neural Networks (RNNs) within the Reservoir Computing (RC) framework, popular for their fast and efficient learning. However, traditional ESNs often struggle with long-term information processing. In this paper, we introduce a novel class of deep untrained RNNs based on temporal residual connections, called Deep Residual Echo State Networks (DeepResESNs). We show that leveraging a hierarchy of untrained residual recurrent layers significantly boosts memory capacity and long-term temporal modeling. For the temporal residual connections, we consider different orthogonal configurations, including randomly generated and fixed-structure configurations, and we study their effect on network dynamics. A thorough mathematical analysis outlines necessary and sufficient conditions to ensure stable dynamics within DeepResESN. Our experiments on a variety of time series tasks showcase the advantages of the proposed approach over traditional shallow and deep RC.