Heterogeneous density-based clustering with a dual-functional memristive array-Reference-Cited by-同舟云学术

Heterogeneous density-based clustering with a dual-functional memristive array

Published:2024 Issue: Volume: Page:
ISSN:2051-6347
Container-title:Materials Horizons
language:en
Short-container-title:Mater. Horiz.

Author:

Shin Dong Hoon¹,Cheong Sunwoo¹,Lee Soo Hyung¹,Jang Yoon Ho¹,Park Taegyun¹,Han Janguk¹,Shim Sung Keun¹,Kim Yeong Rok¹,Han Joon-Kyu¹²,Baek In Kyung¹,Ghenzi Néstor¹³,Hwang Cheol Seong¹^ORCID

Affiliation:

1. Department of Materials Science and Engineering and Inter-university Semiconductor Research Center, College of Engineering, Seoul National University, Seoul, 08826, Republic of Korea

2. System Semiconductor Engineering and the Department of Electronic Engineering, Sogang University, Seoul, Republic of Korea

3. Universidad de Avellaneda UNDAV and Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET), Mario Bravo 1460, Avellaneda, Buenos Aires 1872, Argentina

Abstract

A reconfigurable dual-mode memristive array was utilized for the proposed heterogeneous density-based clustering. Both digital and analog modes were analyzed, and the algorithm was verified through vector–matrix multiplication in both modes.

Funder

National Research Foundation of Korea

Publisher

Royal Society of Chemistry (RSC)

Link

http://pubs.rsc.org/en/content/articlepdf/2024/MH/D4MH00300D

Reference44 articles.

1. Memristor‐Based Analog Computation and Neural Network Classification with a Dot Product Engine

2. Memristive crossbar arrays for brain-inspired computing

3. Fully hardware-implemented memristor convolutional neural network

4. Power-efficient combinatorial optimization using intrinsic noise in memristor Hopfield neural networks

5. Memristor networks for real-time neural activity analysis