Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting
This work addresses the need for comprehensive performance analysis of deep reservoir computing models for researchers in time series forecasting, though it appears incremental as it builds on existing echo state network frameworks.
The study analyzed the performance of wide and deep echo state networks for multiscale spatiotemporal time series forecasting, examining how partitioning neurons and using parallel reservoir pathways affect results across various datasets with nonlinear dynamics.
Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While these networks are increasingly applied to nontrivial forecasting tasks, there is a need for comprehensive performance analysis of deep reservoirs. In this work, we study the influence of partitioning neurons given a budget and the effect of parallel reservoir pathways across different datasets exhibiting multi-scale and nonlinear dynamics.