.png){kind=icon}
.png){kind=icon}
Return
Unlocking neuromorphic memory through functional device
.png){kind=icon}
PRE
AI
DOI：10.1016/j.device.2025.100875.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Achieving high energy efficiency and fast processing speed remains a crucial challenge in artificial intelligence applications. Neuromorphic computing (NC), characterized by its emulation of biological neural networks, presents a promising approach to developing energy-efficient and high-performance systems. Emerging memory devices, including floating-gate transistors (FGTs), ferroelectric transistors, and resistive random-access memory (RRAM), have attracted considerable attention for their ability to effectively emulate neuronal and synaptic functions. Here, we discuss the development of memory technologies and their potential integration into future neuromorphic systems.