# Optimizing Memory in Reservoir Computers

arXiv: https://arxiv.org/abs/2201.01605 · HTML: https://mlsanity.com/paper/2201.01605/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jan 2022.

## Built on by (most cited first, 13 of 13)

- [Catch-22s of reservoir computing](https://mlsanity.com/paper/2210.10211/) (2022)
- [Inferring Attracting Basins of Power System with Machine Learning](https://mlsanity.com/paper/2305.14374/) (2023)
- [Edge of stability echo state networks](https://mlsanity.com/paper/2308.02902/) (2023)
- [Machine-learning parameter tracking with partial state observation](https://mlsanity.com/paper/2311.09142/) (2023)
- [Time Shifts to Reduce the Size of Reservoir Computers](https://mlsanity.com/paper/2205.02267/) (2022)
- [Digital twins of nonlinear dynamical systems](https://mlsanity.com/paper/2210.06144/) (2022)
- [Digital twins of nonlinear dynamical systems: A perspective](https://mlsanity.com/paper/2309.11461/) (2023)
- [Universal Approximation of Linear Time-Invariant (LTI) Systems through RNNs: Power of Randomness in Reservoir Computing](https://mlsanity.com/paper/2308.02464/) (2023)
- [HypER: Hyperbolic Echo State Networks for Capturing Stretch-and-Fold Dynamics in Chaotic Flows](https://mlsanity.com/paper/2508.18196/) (2025)
- [Vestibular reservoir computing](https://mlsanity.com/paper/2604.09943/) (2026)
- [Effective Training Principles of Physical Reservoirs](https://mlsanity.com/paper/2606.10130/) (2026)
- [Long-Memory Reservoir Computing for Data-Scarce Dengue Forecasting](https://mlsanity.com/paper/2607.11272/) (2026)
- [Nanoparticle Networks for Neuromorphic Computing](https://mlsanity.com/paper/2607.27844/) (2026)

## Abstract (arXiv)

A reservoir computer is a way of using a high dimensional dynamical system for computation. One way to construct a reservoir computer is by connecting a set of nonlinear nodes into a network. Because the network creates feedback between nodes, the reservoir computer has memory. If the reservoir computer is to respond to an input signal in a consistent way (a necessary condition for computation), the memory must be fading; that is, the influence of the initial conditions fades over time. How long this memory lasts is important for determining how well the reservoir computer can solve a particular problem. In this paper I describe ways to vary the length of the fading memory in reservoir computers. Tuning the memory can be important to achieve optimal results in some problems; too much or too little memory degrades the accuracy of the computation.