arXiv subjects

Humza Syed

Publications and source records attributed to Humza Syed.

2 recordsLinked to original sources

arXiv2019

Analysis of Wide and Deep Echo State Networks for Multiscale Spatiotemporal Time Series Forecasting

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.

eess.SP↗

arXiv2018

Mod-DeepESN: Modular Deep Echo State Network

Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex tasks that are characterized by multi-scale structures. In this research, an intrinsic plasticity-infused modular deep echo state network architecture is proposed to solve complex and multiple timescale temporal tasks. It outperforms state-of-the-art for time series prediction tasks.

cs.LG↗