CMOS-Compatible Embedded Artificial Synaptic Device (eASD) for Neuromorphic Computing and AI Applications

• Published in: IEEE transactions on electron devices Vol. 71; no. 2; pp. 1 - 7
• Main Authors: Huang, Yao-Hung, Yu, Hsin-Yuan, Chih, Yue-Der, Wang, Yih, King, Ya-Chin, Lin, Chrong Jung
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.02.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Artificial neural networks; CMOS; computing-in-memory; embedded memory; high-k metal gate (HKMG); Logic gates; Memristors; neural network (NN); Neural networks; neuromorphic; Reliability; resistive random access memory (RRAM); Switches; Synapses; Transistors

The research showcases innovative embedded artificial synaptic devices (eASDs) implemented in a CMOS logic platform. These eASD devices demonstrate a large sensing window, exceptional endurance, and reliable data retention. Moreover, they can seamlessly integrate into neural network (NN) circuits, e...