相关实验视频
Updated: Jun 19, 2026

07:46
A Method for Growing Bio-memristors from Slime Mold
Published on: November 2, 2017
9.2K
对于记忆神经网络的错误意识概率训练
Jinchang Liu1, Jian Lu1, Shuangzhu Tang1
1Zhejiang Laboratory, Hangzhou, China.
Nature communications
|December 12, 2025
概括
由于设备噪音,模拟内存计算设备面临训练挑战. 一种错误感知概率更新 (EaPU) 方法克服了这一点,使得在memristor硬件上深度神经网络的高效训练能够节省大量能源.
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:
- 模拟内存计算设备通过利用物理定律进行计算,提供高能效.
- 模拟硬件中的随机设备特征与像反向传播 (BP) 等确定性训练算法发生冲突,阻碍了性能.
- 在模拟设备物理和传统的深度学习培训方法之间存在不匹配.
研究的目的:
- 为训练模拟内存计算设备提出和验证一个错误感知概率更新 (EaPU) 方法.
- 在模拟硬件培训中解决算法-设备不匹配问题.
- 通过对memristor系统进行深度神经网络训练来证明显著的能源减少和性能提高.
主要方法:
- 开发了一个错误感知概率更新 (EaPU) 方法,利用设备编写噪声进行重量更新.
- 经过实验验证的EaPU在180nm的memristor系统上用于图像消噪和超分辨率任务.
- 在包括ResNet和Vision Transformers在内的深度学习模型上模拟EaPU性能.
主要成果:
- EaPU将重量更新降低到传统BP的1‰以下,精度损失最小.
- 在EaPU培训中,memristor系统的准确性提高了60%以上.
- 与基于BP的memristor训练和MADEM相比,EaPU展示了大量的节能:~50.54×和13.23×较低的训练能量.
- 基于EaPU的memristor硬件实现了几乎6个数量级低于GPU的训练能量.
结论:
- EaPU提供了一种精确有效的方法来训练基于模拟设备的深度神经网络.
- 提出的方法有效地弥合了随机模拟硬件和决定性训练算法之间的差距.
- EaPU代表了节能神经形态计算和人工智能硬件的重大进步.
相关概念视频
Random and Systematic Errors
Scientists always try their best to record measurements with the utmost accuracy and precision. However, sometimes errors do occur. These errors can be random or systematic. Random errors are observed due to the inconsistency or fluctuation in the measurement process, or variations in the quantity itself that is being measured. Such errors fluctuate from being greater than or less than the true value in repeated measurements. Consider a scientist measuring the length of an earthworm using a...
Errors In Hypothesis Tests
When performing a hypothesis test, there are four possible outcomes depending on the actual truth (or falseness) of the null hypothesis and the decision to reject or not.
Detection of Gross Error: The Q Test
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
Random and Systematic Errors
Scientists always try their best to record measurements with the utmost accuracy and precision. However, sometimes errors do occur. These errors can be random or systematic. Random errors are observed due to the inconsistency or fluctuation in the measurement process, or variations in the quantity itself that is being measured. Such errors fluctuate from being greater than or less than the true value in repeated measurements. Consider a scientist measuring the length of an earthworm using a...
False Memories
False memories represent a cognitive distortion in which individuals recall events that did not happen, or remember them in an altered form. This phenomenon highlights the brain's constructive nature in processing and recalling memories, emphasizing that memory is not a perfect representation of past events but rather a dynamic reconstruction influenced by various factors.
One primary source of false memories is misattribution, where individuals incorrectly associate external information with...
One primary source of false memories is misattribution, where individuals incorrectly associate external information with...
Survival Tree
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a survival tree begins...
Building a Survival Tree
Constructing a survival tree begins...

