2023
DOI: 10.1088/2634-4386/acd20d
|View full text |Cite
|
Sign up to set email alerts
|

The van der Pol physical reservoir computer

Abstract: The van der Pol oscillator has historical and practical significance to spiking neural networks. It was proposed as one of the first models for heart oscillations, and it has been used as the building block for spiking neural networks. Furthermore, the van der Pol oscillator is also readily implemented as an electronic circuit. For these reasons, we chose to implement the van der Pol oscillator as a physical reservoir computer to highlight its computational ability, even when it is not in an array. The van der… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2024
2024
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(2 citation statements)
references
References 57 publications
0
2
0
Order By: Relevance
“…In the generative regime, the implementation of Step 7 of the computational procedure outlined in Section 2.1 corresponds to the introduction of a feedback loop from the output of the RC system to its input. Subsequently, the reservoir can be considered to be a selfoscillator [84], which is an established fact [85].…”
Section: Advantages For Generative Mode Operationmentioning
confidence: 99%
“…In the generative regime, the implementation of Step 7 of the computational procedure outlined in Section 2.1 corresponds to the introduction of a feedback loop from the output of the RC system to its input. Subsequently, the reservoir can be considered to be a selfoscillator [84], which is an established fact [85].…”
Section: Advantages For Generative Mode Operationmentioning
confidence: 99%
“…The generated time series is then split into two parts used at the training and testing stages, respectively. In this test task, the reservoir operates in the generative mode, also known as the freerunning forecast, where the output produced by a trained reservoir in the previous time step serves as an input at the next time step, i.e., u n+1 = y n [21] (in other words, the reservoir acts as a self-generator [58]). We stress that we deliberately choose to test the reservoir in the generative mode because, as shown in Refs.…”
Section: Chaotic Times-series Forecastingmentioning
confidence: 99%