Hardware implementation of memristor-based artificial neural networks

• Published in: Nature communications Vol. 15; no. 1; pp. 1974 - 40
• Main Authors: Aguirre, Fernando, Sebastian, Abu, Le Gallo, Manuel, Song, Wenhao, Wang, Tong, Yang, J. Joshua, Lu, Wei, Chang, Meng-Fan, Ielmini, Daniele, Yang, Yuchao, Mehonic, Adnan, Kenyon, Anthony, Villena, Marco A., Roldán, Juan B., Wu, Yuting, Hsu, Hung-Hsi, Raghavan, Nagarajan, Suñé, Jordi, Miranda, Enrique, Eltawil, Ahmed, Setti, Gianluca, Smagulova, Kamilya, Salama, Khaled N., Krestinskaya, Olga, Yan, Xiaobing, Ang, Kah-Wee, Jain, Samarth, Li, Sifan, Alharbi, Osamah, Pazos, Sebastian, Lanza, Mario
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 04.03.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 639/166/987; 639/301/1005/1007; 639/925/927/1007; Artificial intelligence; Artificial neural networks; CMOS; Data communication; Deep learning; Energy efficiency; Hardware; Humanities and Social Sciences; Machine learning; Memory devices; Memristors; multidisciplinary; Neural networks; Parallel processing; Performance evaluation; Performance measurement; Power management; Review; Review Article; Science; Science (multidisciplinary)

Artificial Intelligence (AI) is currently experiencing a bloom driven by deep learning (DL) techniques, which rely on networks of connected simple computing units operating in parallel. The low communication bandwidth between memory and processing units in conventional von Neumann machines does not...