Feature-Based Echo-State Networks: A Step Towards Interpretability and Minimalism in Reservoir Computer

arXiv:2403.19806v1 Announce Type: new
Abstract: This paper proposes a novel and interpretable recurrent neural-network structure using the echo-state network (ESN) paradigm for time-series prediction. While the traditional ESNs perform well for dynamical systems prediction, it needs a large dynamic reservoir with increased computational complexity. It also lacks interpretability to discern contributions from different input combinations to the output. Here, a systematic reservoir architecture is developed using smaller parallel reservoirs driven by different input combinations, known as features, and then they …

abstract arxiv complexity computational computer cs.lg cs.sy dynamic echo eess.sy feature interpretability network networks novel paper paradigm prediction series state systems type