EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Natural Language Processing Using Reservoir Computers: Network-Theoretic Analysis and Information Flow

Hyeongmo Kim, Wooseung Yoon, Junhyuk Woo, Chaehee Kim, Sangeun Lee, Seungyeon Ji, Joonho Paik, Jibaek Lim, Soyeon Caren Han, Hyunsuk Chung, Sangwook Yi, Kyungreem Han

Applied Sciences · 30.10.2026 · 16 (21) · 10791

DOI: 10.3390/app162110791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 30.10.2026. Verfasst von Hyeongmo Kim und 11 weiteren Autor:innen. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, Korea Institute of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reservoir computing (RC) is a highly efficient time-series processing neural network model that can be applied to a wide range of real-world applications, including natural language processing. This study offers physical perspectives on how RC processes natural language, focusing on network structure and information flow. The character memorization task on Shakespeare’s works (i.e., a 9,044,939-character database) revealed that memory retention largely depends on the network’s structural properties. However, structural property measures such as clustering coefficient, shortest path length, and degree fail to capture the prediction mechanism. Predicting the following character mainly relies on optimal effective memory depth, revealed by Layer-wise relevance propagation analysis. This information-centered view, rather than apparent network topologies, may strongly support the notion of a physical model-based understanding of Large Language Models.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation
  • Korea Institute of Science and Technology

Zitieren

APA

Kim, H., Yoon, W., Woo, J., Kim, C., Lee, S., Ji, S., Paik, J., Lim, J., Han, S. C., Chung, H., Yi, S., & Han, K. (2026). Natural Language Processing Using Reservoir Computers: Network-Theoretic Analysis and Information Flow. Applied Sciences, 16(21), 10791. https://doi.org/10.3390/app162110791

Vancouver

Kim H, Yoon W, Woo J, Kim C, Lee S, Ji S, et al. Natural Language Processing Using Reservoir Computers: Network-Theoretic Analysis and Information Flow. Applied Sciences. 2026;16(21):10791. doi:10.3390/app162110791

BibTeX
@article{Kim2026,
  author = {Kim, Hyeongmo and Yoon, Wooseung and Woo, Junhyuk and Kim, Chaehee and Lee, Sangeun and Ji, Seungyeon and Paik, Joonho and Lim, Jibaek and Han, Soyeon Caren and Chung, Hyunsuk and Yi, Sangwook and Han, Kyungreem},
  title = {Natural Language Processing Using Reservoir Computers: Network-Theoretic Analysis and Information Flow},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {10791},
  doi = {10.3390/app162110791}
}
Kostenlos starten →