Echo State Property upon Noisy Driving Input
Complexity · 16.02.2024 · 2024 · 1-15
DOI: 10.1155/2024/5593925 ↗Kurz gefasst
Fachartikel in der Zeitschrift Complexity, erschienen am 16.02.2024. Verfasst von Junhyuk Woo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Institute of Science and Technology, Ministry of Science, ICT and Future Planning.
Abstract (Originalsprache)
The echo state property (ESP) is a key concept for understanding the working principle of the most widely used reservoir computing model, the echo state network (ESN). The ESP is achieved most of the operation time under general conditions, yet the property is lost when a combination of driving input signals and intrinsic reservoir dynamics causes unfavorable conditions for forgetting the initial transient state. A widely used treatment, setting the spectral radius of the weight matrix below the unity, is not sufficient as it may not properly account for the nature of driving inputs. Here, we characterize how noisy driving inputs affect the dynamical properties of an ESN and the empirical evaluation of the ESP. The standard ESN with a hyperbolic tangent activation function is tested using the MNIST handwritten digit datasets at different additive white Gaussian noise levels. The correlations among the neurons, input mapping, and memory capacity of the reservoir nonlinearly decrease with the noise level. These trends agree with the deterioration of the MNIST classification accuracy against noise. In addition, the ESP index for noisy driving input is developed as a tool to help easily assess ESPs in practical applications. Bifurcation analysis explicates how the noise destroys an asymptotical convergence in an ESN and confirms that the proposed index successfully captures the ESP against noise. These results pave the way for developing noise-robust reservoir computing systems, which may promote the validity and utility of reservoir computing for real-world machine learning applications.
Förderung
- Korea Institute of Science and Technology
- Ministry of Science, ICT and Future Planning
Zitieren
APA
Woo, J., Kim, H., Kim, S. H., & Han, K. (2024). Echo State Property upon Noisy Driving Input. Complexity, 2024, 1-15. https://doi.org/10.1155/2024/5593925
Vancouver
Woo J, Kim H, Kim SH, Han K. Echo State Property upon Noisy Driving Input. Complexity. 2024;2024:1-15. doi:10.1155/2024/5593925
BibTeX
@article{Woo2024,
author = {Woo, Junhyuk and Kim, Hyeongmo and Kim, Soon Ho and Han, Kyungreem},
title = {Echo State Property upon Noisy Driving Input},
journal = {Complexity},
year = {2024},
volume = {2024},
pages = {1--15},
doi = {10.1155/2024/5593925}
}
EUVIMED