预测一致性规范化与噪音标签的学习基于对比的集群.
Xinkai Sun1,2, Sanguo Zhang1,2, Shuangge Ma3
1School of Mathematics Sciences, University of Chinese Academy of Sciences, Beijing 100049, China.
这项研究引入了一种新的方法,通过提高预测一致性来提高分类准确度,尽管标签噪声. 它使用调整的双对比集群 (TCC) 和基于原型的规范化来识别类似的样本并减轻噪声效应.
科学领域:
- 机器学习 机器学习
- 计算机科学 计算机科学
- 人工智能的人工智能
背景情况:
- 标签噪声通过破坏预测的一致性和降低准确性,显著降低了神经网络在分类任务中的性能.
- 识别类似的样本对于有效的降噪至关重要,但仍然是现有方法的主要挑战.
研究的目的:
- 开发一种新的预测一致性规范化技术,以减轻标签噪声对神经网络分类的影响.
- 通过将其正式化为一个集群问题来解决识别类似样本的挑战.
主要方法:
- 采用双对比分类 (TCC) 进行类似样本识别,通过调整分类先验与标签信息来增强.
- 基于调整的TCC结果构建了集群原型,并制定了基于原型的规范化术语,以提高预测一致性.
- 在各种噪声率的基准数据集上评估了该方法的有效性.
主要成果:
- 在不同的标签噪声场景下显著提高了分类准确性.
- 证实,拟议的规范化术语有效地减轻了标签噪声的不利影响.
- 证明调整后的TCC可以提高类似样本识别的质量.
结论:
- 新的预测一致性规范化有效地打击了分类任务中的标签噪声.
- 整合调整的TCC和基于原型的规范化提供了一个强大的解决方案,用于在杂的数据环境中改善模型性能.
更多相关视频
12:27Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
Published on: February 15, 2017
14:27Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
相关概念视频
Prediction Intervals
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.
Improving Translational Accuracy
Regression Toward the Mean
Difference from Background: Limit of Detection
The LOD indicates the presence or absence...
Generalization, Discrimination, and Extinction
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Expected Frequencies in Goodness-of-Fit Tests
