# Mod-DeepESN: Modular Deep Echo State Network

arXiv: https://arxiv.org/abs/1808.00523 · HTML: https://mlsanity.com/paper/1808.00523/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2018.

## Built on by (most cited first, 3 of 3)

- [Recurrent Stochastic Configuration Networks for Temporal Data Analytics](https://mlsanity.com/paper/2406.16959/) (2024)
- [PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks](https://mlsanity.com/paper/2103.04807/) (2021)
- [An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifiers](https://mlsanity.com/paper/2606.14739/) (2026)

## Abstract (arXiv)

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.