Premium
Ionotronic Neuromorphic Devices for Bionic Neural Network Applications
Author(s) -
Yu Fei,
Zhu Li Qiang
Publication year - 2019
Publication title -
physica status solidi (rrl) – rapid research letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.786
H-Index - 68
eISSN - 1862-6270
pISSN - 1862-6254
DOI - 10.1002/pssr.201970025
Subject(s) - neuromorphic engineering , memristor , computer science , artificial neural network , bottleneck , von neumann architecture , transistor , artificial intelligence , computer architecture , electronic engineering , electrical engineering , engineering , embedded system , voltage , operating system
Transistor‐ and memristor‐based neuromorphic devices have unique non‐volatile characteristics. They can overcome the von Neumann bottleneck and can act as building blocks for bionic neural networks. The ionotronic devices, transmitting electronic signals through the migration of ionic species in dielectric and resistive switching electrolyte, have unique ionic relaxation behaviors and biology‐comparable relaxation time scales, which impart them great potentials in building bionic neural networks and realizing hardware‐based artificial intelligence (AI)/AI chips. In article no. 1800674 , Fei Yu and Li Qiang Zhu review recent achievements in ionotronic neuromorphic devices and forecast their potential applications in multifunctional intelligent artificial perception learning systems and AI chips. Fundamental operation mechanisms, basic electrical characteristics and variable conductance functionality of the ionotronic neuromorphic devices are introduced. Various synaptic plasticities and advanced neural functions mimicked on ionotronic devices are summarized.