Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting
Signal Processing
2019-08-23 v1 Machine Learning
Neural and Evolutionary Computing
Machine Learning
Abstract
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.
Cite
@article{arxiv.1908.08380,
title = {Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting},
author = {Zachariah Carmichael and Humza Syed and Dhireesha Kudithipudi},
journal= {arXiv preprint arXiv:1908.08380},
year = {2019}
}
Comments
10 pages, 10 figures, Proceedings of the Neuro-inspired Computational Elements Workshop (NICE '19), March 26-28, 2019, Albany, NY, USA