基于MoS22T0C DRAM用于神经元和突触的双模式神经形态设备
Zhejia Zhang1, Saifei Gou1, Qihao Chen1
1State Key Laboratory of Integrated Chip and Systems, School of Microelectronics, Fudan University, Shanghai, 200433, P. R. China.
Small (Weinheim an der Bergstrasse, Germany)
|September 18, 2025
概括
研究人员开发了用于高效人工神经网络 (ANN) 的新型二硫化物 (MoS2) 设备. 这些低功耗,高密度的设备模仿大脑功能,在手写数字识别方面达到高精度.
科学领域:
- 材料科学 材料科学 材料科学
- 神经科学是一个神经科学.
- 计算机工程 计算机工程
背景情况:
- 人工神经网络 (ANN) 通过模仿生物系统,显示出低功耗计算的前景.
- 对ANN的硬件实现在高密度和功率效率的突触和神经元功能集成方面面临挑战.
- 生物灵感动态对于先进的神经形态计算至关重要.
研究的目的:
- 提出和演示用于神经形态计算应用的晶圆尺度MoS2 2T0C设备.
- 为了实现在突触和神经元模拟的挥发性和准非挥发性模式之间的稳定切换.
- 在保留时间,线性,速度和能源效率方面实现高性能.
主要方法:
- 晶圆尺度的二硫化物 (MoS2) 2-晶体管-0-电容器 (2T0C) 设备的制造.
- 设备性能作为人工突触和神经元的表征.
- 使用一系列这些双模式设备构建一个尖端神经网络 (SNN).
主要成果:
- 该MoS2 2T0C设备展示了突触功能,具有>40s保留时间,高线性,500ns编程速度和6pJ写入能量.
- 作为一个神经元,该设备表现出漏电整合和燃烧 (LIF) 行为,能量消耗升15pJ.
- 在100个训练时代后,SNN模型在MNIST数据集上实现了92.88%的识别精度.
结论:
- 晶圆尺度的MoS2 2T0C设备为高效,高密度的神经形态硬件提供了一个有前途的平台.
- 这些设备的双模式功能有效地模拟了突触和神经元功能.
- 这项技术可以开发先进的尖端神经网络,用于复杂的计算任务.
更多相关视频
08:57Hybrid Microdrive System with Recoverable Opto-Silicon Probe and Tetrode for Dual-Site High Density Recording in Freely Moving Mice
Published on: August 10, 2019
11.5K
10:32Design, Surface Treatment, Cellular Plating, and Culturing of Modular Neuronal Networks Composed of Functionally Inter-connected Circuits
Published on: April 15, 2015
8.9K
相关概念视频
MOS Capacitor
1.5K
A Metal-Oxide-Semiconductor (MOS) capacitor is a fundamental structure used extensively in semiconductor device technology, particularly in the fabrication of integrated circuits and MOSFETs (metal-oxide-semiconductor field-effect transistors). The MOS capacitor consists of three layers: a metal gate, a dielectric oxide, and a semiconductor substrate.
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
The metal gate is typically made from highly conductive materials such as aluminum or polysilicon. Beneath the metal gate lies a thin layer of...
1.5K
MOSFET: Enhancement Mode
792
Enhancement-mode MOSFETs are pivotal components in electronics, distinguished by their capacity to act as highly efficient switches. They are part of the larger family of metal-oxide Semiconductor Field-Effect Transistors (MOSFETs). They are available in two types: p-channel and n-channel, each tailored to specific polarity operations.
In their basic form, enhancement-mode MOSFETs are typically non-conductive when the gate-source voltage (Vgs) is zero. This default 'off' state means no...
In their basic form, enhancement-mode MOSFETs are typically non-conductive when the gate-source voltage (Vgs) is zero. This default 'off' state means no...
792
MOSFET
1.2K
The Metal-Oxide-Semiconductor Field-Effect Transistor (MOSFET) plays a pivotal role in modern electronics thanks to its versatility and efficiency in controlling electrical currents. This device, also known as IGFET, MISFET, and MOSFET, has three main terminals: the Source, Drain, and Gate. MOSFETs are classified into n-channel or p-channel types based on the doping characteristics of their substrate and the source or drain regions.
In an n-MOSFET, the structure includes n-type source and drain...
In an n-MOSFET, the structure includes n-type source and drain...
1.2K
MOSFET: Depletion Mode
823
Depletion-mode MOSFETs represent a unique subset of MOSFET technology, functioning fundamentally differently from their enhancement-mode counterparts. Unlike enhancement MOSFETs, which require a positive gate-source voltage (Vgs) to turn on, depletion-mode MOSFETs are inherently conductive and "normally on" devices.
The primary characteristic of depletion-mode MOSFETs is their ability to conduct current between the drain and source terminals without gate bias. This inherent conductivity...
The primary characteristic of depletion-mode MOSFETs is their ability to conduct current between the drain and source terminals without gate bias. This inherent conductivity...
823
Neural Circuits
2.7K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.7K
Neurons: The Axon
7.0K
Axons are long, cytoplasmic processes of nerve cells capable of propagating electrical impulses known as action potentials. The cytoplasm or axoplasm of an axon contains neurofibrils, neurotubules, small vesicles, lysosomes, mitochondria, and various enzymes, all encased within the axolemma, the plasma membrane of the axon.
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment....
The axon attaches to the cell body at a cone-shaped elevation called the axon hillock. The initial part of the axon, closest to the hillock, is known as the initial segment....
7.0K
