# Time-shift selection for reservoir computing using a rank-revealing QR algorithm

arXiv: https://arxiv.org/abs/2211.17095 · HTML: https://mlsanity.com/paper/2211.17095/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 43 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Builds on (most cited first, 8 of 8)

- [Model-Free Control of Dynamical Systems with Deep Reservoir Computing](https://mlsanity.com/paper/2010.02285/) (2020)
- [Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation](https://mlsanity.com/paper/1610.06268/) (2016)
- [Performance boost of time-delay reservoir computing by non-resonant clock cycle](https://mlsanity.com/paper/1905.02534/) (2019)
- [Photonic neural field on a silicon chip: large-scale, high-speed neuro-inspired computing and sensing](https://mlsanity.com/paper/2105.10672/) (2021)
- [Adding Filters to Improve Reservoir Computer Performance](https://mlsanity.com/paper/2008.10633/) (2020)
- [Reservoir Computers with Random and Optimized Time-Shifts](https://mlsanity.com/paper/2108.12765/) (2021)
- [Takens-inspired neuromorphic processor: a downsizing tool for random recurrent neural networks via feature extraction](https://mlsanity.com/paper/1907.03122/) (2019)
- [Time Shifts to Reduce the Size of Reservoir Computers](https://mlsanity.com/paper/2205.02267/) (2022)

## Built on by (most cited first, 1 of 1)

- [Detecting disturbances in network-coupled dynamical systems with machine learning](https://mlsanity.com/paper/2307.12771/) (2023)

## Abstract (arXiv)

Reservoir computing, a recurrent neural network paradigm in which only the output layer is trained, has demonstrated remarkable performance on tasks such as prediction and control of nonlinear systems. Recently, it was demonstrated that adding time-shifts to the signals generated by a reservoir can provide large improvements in performance accuracy. In this work, we present a technique to choose the time-shifts by maximizing the rank of the reservoir matrix using a rank-revealing QR algorithm. This technique, which is not task dependent, does not require a model of the system, and therefore is directly applicable to analog hardware reservoir computers. We demonstrate our time-shift selection technique on two types of reservoir computer: one based on an opto-electronic oscillator and the traditional recurrent network with a tanh activation function. We find that our technique provides improved accuracy over random time-shift selection in essentially all cases.