# RcTorch: a PyTorch Reservoir Computing Package with Automated Hyper-Parameter Optimization

arXiv: https://arxiv.org/abs/2207.05870 · HTML: https://mlsanity.com/paper/2207.05870/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 40 references that are in the map.
- First posted on arXiv 12 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Scalable Global Optimization via Local Bayesian Optimization](https://mlsanity.com/paper/1910.01739/) (2019)
- [Federated Bayesian Optimization via Thompson Sampling](https://mlsanity.com/paper/2010.10154/) (2020)
- [Hamiltonian neural networks for solving equations of motion](https://mlsanity.com/paper/2001.11107/) (2020)
- [Theory of neuromorphic computing by waves: machine learning by rogue waves, dispersive shocks, and solitons](https://mlsanity.com/paper/1912.07044/) (2019)
- [Reservoir computing model of two-dimensional turbulent convection](https://mlsanity.com/paper/2001.10280/) (2020)
- [Unsupervised Reservoir Computing for Solving Ordinary Differential Equations](https://mlsanity.com/paper/2108.11417/) (2021)
- [Efficient Optimization of Echo State Networks for Time Series Datasets](https://mlsanity.com/paper/1903.05071/) (2019)
- [Bayesian Optimization with Unknown Search Space](https://mlsanity.com/paper/1910.13092/) (2019)
- [Input-to-State Representation in linear reservoirs dynamics](https://mlsanity.com/paper/2003.10585/) (2020)

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

- [Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input](https://mlsanity.com/paper/2401.14371/) (2024)
- [Long-term prediction of El Ni~no-Southern Oscillation using reservoir computing with data-driven realtime filter](https://mlsanity.com/paper/2501.17781/) (2025)
- [Boosting Reservoir Computing with Brain-inspired Adaptive Dynamics](https://mlsanity.com/paper/2504.12480/) (2025)

## Abstract (arXiv)

Reservoir computers (RCs) are among the fastest to train of all neural networks, especially when they are compared to other recurrent neural networks. RC has this advantage while still handling sequential data exceptionally well. However, RC adoption has lagged other neural network models because of the model's sensitivity to its hyper-parameters (HPs). A modern unified software package that automatically tunes these parameters is missing from the literature. Manually tuning these numbers is very difficult, and the cost of traditional grid search methods grows exponentially with the number of HPs considered, discouraging the use of the RC and limiting the complexity of the RC models which can be devised. We address these problems by introducing RcTorch, a PyTorch based RC neural network package with automated HP tuning. Herein, we demonstrate the utility of RcTorch by using it to predict the complex dynamics of a driven pendulum being acted upon by varying forces. This work includes coding examples. Example Python Jupyter notebooks can be found on our GitHub repository https://github.com/blindedjoy/RcTorch and documentation can be found at https://rctorch.readthedocs.io/.