Related Experiment Video
Updated: May 13, 2025
08:07
Assembly and Characterization of Biomolecular Memristors Consisting of Ion Channel-doped Lipid Membranes
Published on: March 9, 2019
7.7K
Low-Power Memristor for Neuromorphic Computing: From Materials to Applications.
Zhipeng Xia1,2, Xiao Sun1,2, Zhenlong Wang1,2
1School of Integrated Circuits, Shandong University, Jinan, 250100, People's Republic of China.
Nano-Micro Letters
|April 14, 2025
Summary
This review explores low-power memristors for neuromorphic computing. It covers device structures, materials, arrays, and applications in advanced storage, logic, and analogue computing, highlighting future challenges.
Area of Science:
- Materials Science
- Electrical Engineering
- Computer Science
Background:
- Memristors are emerging memory devices with significant potential for low-power neuromorphic computing.
- Their unique characteristics offer advantages over traditional computing architectures.
Purpose of the Study:
- To review the application of low-power memristors in various aspects of neuromorphic computing.
- To discuss device concepts, materials, array structures, and potential applications.
Main Methods:
- Introduction to memristor device concepts and structures.
- Discussion on functional materials (ion transport, phase change, magnetoresistive, ferroelectric).
- Analysis of 1T1R and 1S1R crossbar arrays and edge computing memristor chips.
Main Results:
- Memristors enable advanced multi-value storage, digital logic gates, and analogue neuromorphic computing.
- Low-power memristor applications are detailed, including their integration into edge computing chips.
Conclusions:
- Low-power memristors are crucial for the advancement of neuromorphic computing.
- Further research is needed to overcome challenges and realize the full potential of memristor-based neuromorphic systems.
