相关实验视频
Updated: May 20, 2025

07:38
Author Spotlight: Modular Neuronal Networks for Analyzing Brain Functions
Published on: June 7, 2024
1.4K
分离策略以分离训练和推理,使用由神经元和混合突触组成的三维神经形态硬件
Jung-Woo Lee1,2, See-On Park1, Seong-Yun Yun1
1School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Daejeon, Yuseong-gu 34141, Republic of Korea.
ACS nano
|March 26, 2025
概括
这项研究引入了一种新的3D神经形态硬件设计,使用专门的突触设备将训练和推理分开. 这种混合方法提高了尖端神经网络 (SNN) 的能源效率和紧性.
科学领域:
- 神经形态工程的神经形态工程
- 材料科学 材料科学 材料科学
- 计算机科学 计算机科学
背景情况:
- 神经元和突触设备的单立体3D集成为节能和紧的神经形态硬件提供了一条道路.
- 目前面临的挑战包括优化训练和推理的性能,这需要不同的突触装置特征 (耐力与保留).
研究的目的:
- 提出和演示一个解策略,用于训练和推理在单立体集成的3D神经形态硬件.
- 通过使用专门的突触设备来实现可靠的尖端神经网络 (SNN) 操作,用于不同的计算阶段.
主要方法:
- 层层地制造3D神经形态硬件.
- 单晶体管神经元 (1T神经元) 的集成.
- 整合了两种不同的突触类型:基于充电陷的单薄膜晶体管突触 (1TFT突触) 用于推断和记忆器突触 (1M突触) 用于训练.
主要成果:
- 1TFT突触表现出适合推断的长时间保留特性.
- 1M突触表现出强大的耐力重复训练更新.
- 混合架构成功地解了突触功能,使有效的训练和可靠的推理成为可能.
结论:
- 拟议的混合突触架构有效地解决了神经形态硬件中训练和推理的相互矛盾的要求.
- 这种脱战略提高了在单立体3D集成系统上实施的SNN的可靠性和性能.
- 层层的制造方法使不同突触功能的集成在单一3D结构中变得更容易.
相关概念视频
Fast Decoupled and DC Powerflow
143
The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:
143
Neural Circuits
952
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...
952

