A review of memristive reservoir computing for temporal data processing and sensing
InfoScience · 2024-12 · 1 (1)
DOI: 10.1002/inc2.12013 ↗Kurz gefasst
Fachartikel in der Zeitschrift InfoScience, online erschienen am 27.08.2024. Verfasst von Yoon Ho Jang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
Reservoir computing (RC) is a promising paradigm for machine learning that uses a fixed, randomly generated network, known as the reservoir, to process input data. A memristor with fading memory and nonlinearity characteristics was adopted as a physical reservoir to implement the hardware RC system. This article reviews the device requirements for effective memristive reservoir implementation and methods for obtaining higher‐dimensional reservoirs for improving RC system performance. In addition, recent in‐sensor RC system studies, which use a memristor that the resistance is changed by an optical signal to realize an energy‐efficient machine vision, are discussed. Finally, the limitations that the memristive and in‐sensor RC systems encounter when attempting to improve performance further are discussed, and future directions that may overcome these challenges are suggested.
Förderung
- National Research Foundation of Korea
Zitieren
APA
Jang, Y. H., Han, J., & Hwang, C. S. (2024). A review of memristive reservoir computing for temporal data processing and sensing. InfoScience, 1(1). https://doi.org/10.1002/inc2.12013
Vancouver
Jang YH, Han J, Hwang CS. A review of memristive reservoir computing for temporal data processing and sensing. InfoScience. 2024;1(1). doi:10.1002/inc2.12013
BibTeX
@article{Jang2024,
author = {Jang, Yoon Ho and Han, Joon‐Kyu and Hwang, Cheol Seong},
title = {A review of memristive reservoir computing for temporal data processing and sensing},
journal = {InfoScience},
year = {2024},
volume = {1},
number = {1},
doi = {10.1002/inc2.12013}
}
EUVIMED