适应性估计依赖实例的噪声过渡矩阵用于学习与依赖实例的标签噪声
Yuan Wang1, Huaxin Pang2, Ying Qin1
1School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China; Visual Intellgence +X International Cooperation Joint Laboratory of MOE, Beijing, 100044, China.
概括
深度学习中的依赖实例的噪声 (IDN) 是通过一种新的方法来解决的,该方法可以在没有假设的情况下估计依赖实例的噪声过渡矩阵 (IDNT). 这种方法提高了对杂数据集的分类器稳定性.
科学领域:
- 机器学习 机器学习
- 计算机视觉 计算机视觉
- 数据科学数据科学数据科学
背景情况:
- 实例依赖噪声 (IDN) 是现实世界数据集的一个重大挑战,影响深度神经网络的性能.
- 现有的IDN方法通常依赖于用限制性假设或点估计依赖实例的噪声过渡矩阵 (IDNT),从而导致估计错误.
研究的目的:
- 开发一种用于估计依赖实例的噪声过渡矩阵 (IDNT) 的新方法,而不对其形式做出假设或要求点.
- 在存在实例依赖噪声的情况下,提高深度神经网络的稳定性.
主要方法:
- 计算实例-标签混矩阵 (ILCM) 使用实例特征和标签表示之间的相似度得分来捕获噪声特征.
- 适应性结合噪音级别后部与ILCM,按噪声程度加权,用于增强IDNT估计.
- 使用估计的IDNT调整损失函数,以训练更强大的分类器.
主要成果:
- 与合成数据集 (F-MNIST,SVHN,CIFAR-10,CIFAR-100) 上的最先进方法相比,提出的方法显示出更高的性能.
- 在真实世界的噪音数据集 (Clothing1M) 上验证了有效性.
- 该方法成功地减轻了依赖实例的噪声的影响,从而提高了分类准确性.
结论:
- 开发的方法有效地在没有事先假设的情况下估计IDNT,为处理依赖实例的噪声提供了更灵活和更准确的方法.
- 这种技术可以提高深度神经网络的稳定性和在具有复杂噪声模式的数据集上的性能.
- 这些发现表明,开发更具弹性的机器学习模型用于现实世界的应用是一个有希望的方向.
更多相关视频
08:27Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
Published on: January 5, 2024
894
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
7.4K
相关概念视频
00:59Propagation of Uncertainty from Random Error
533
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
533
01:03Prediction Intervals
2.2K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.2K
01:10Propagation of Uncertainty from Systematic Error
373
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
373
01:24One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
225
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
225
01:13Randomized Experiments
6.6K
The randomization process involves assigning study participants randomly to experimental or control groups based on their probability of being equally assigned. Randomization is meant to eliminate selection bias and balance known and unknown confounding factors so that the control group is similar to the treatment group as much as possible. A computer program and a random number generator can be used to assign participants to groups in a way that minimizes bias.
Simple randomization
Simple...
Simple randomization
Simple...
6.6K
01:09Random Variables
11.3K
A random variable is a single numerical value that indicates the outcome of a procedure. The concept of random variables is fundamental to the probability theory and was introduced by a Russian mathematician, Pafnuty Chebyshev, in the mid-nineteenth century.
Uppercase letters such as X or Y denote a random variable. Lowercase letters like x or y denote the value of a random variable. If X is a random variable, then X is written in words, and x is given as a number.
For example, let X = the...
Uppercase letters such as X or Y denote a random variable. Lowercase letters like x or y denote the value of a random variable. If X is a random variable, then X is written in words, and x is given as a number.
For example, let X = the...
11.3K