Research on Memristor-Based Neural Networks
Transactions on Computer Science and Intelligent Systems Research · 2024
DOI: 10.62051/0ra1w557 ↗Kurz gefasst
Fachartikel in der Zeitschrift Transactions on Computer Science and Intelligent Systems Research, 2024. Verfasst von Haozheng Ling. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Memristors, a new kind of resistive device, have attracted considerable attention in recent years because of their nonvolatile nature, low energy consumption, and highly integrated performance. The key theory of the memristor is described, and its application in the structure of neural networks and arithmetic optimization is discussed. First, the fundamental models and operating properties of the memristor are evaluated, with emphasis on its voltage, current, and time variations. This paper reviews the performance of a variety of models based on the concept of memory, which can be used to reduce energy consumption and improve computation efficiency. Additionally, advancements in memristor technology that enhance the scalability and reliability of neural network architectures are explored. An optimal combination of pruning and quantizing is presented, which can greatly decrease the amount of data required by the neural network. Results show that the memristor has great potential to generate high performance, low power, and high efficiency in artificial intelligence applications, making it a promising component in the future of computing technology.
Zitieren
APA
Ling, H. (2024). Research on Memristor-Based Neural Networks. Transactions on Computer Science and Intelligent Systems Research. https://doi.org/10.62051/0ra1w557
Vancouver
Ling H. Research on Memristor-Based Neural Networks. Transactions on Computer Science and Intelligent Systems Research. 2024. doi:10.62051/0ra1w557
BibTeX
@article{Ling2024,
author = {Ling, Haozheng},
title = {Research on Memristor-Based Neural Networks},
journal = {Transactions on Computer Science and Intelligent Systems Research},
year = {2024},
doi = {10.62051/0ra1w557}
}
EUVIMED