基于结构的训练:针对基于相关系数的神经网络的像素错误的训练方法.
Jun Su1,2, Wei He1,2, Yingguan Wang1,2
1Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai 200050, China.
Sensors (Basel, Switzerland)
|October 26, 2024
概括
本研究介绍了影子节点和基于结构的训练方法,用于一次性学习神经网络. 这种方法通过优化网络结构而不是仅仅是参数来提高性能,从而提高目标检测的准确性.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 一次性学习神经网络,没有预训练,由于单个训练样本的信息不足而面临性能限制.
- 现有的网络通常通过反向传播来优化参数,这对于某些架构来说可能是次优的.
研究的目的:
- 提高基于相关系数的神经网络在一次性学习场景中的性能.
- 制定一项新的培训战略,充分利用支持集的全部潜力,并解决网络结构上的局限性.
主要方法:
- 设计三种类型的"影子节点",以提高网络的适应性.
- 提出基于结构的训练方法,通过纠正像素错误来优化网络架构,而不是仅依赖反向传播.
- 专注于培训策略的分支机构,这些分支机构可能会意外地被激活或被禁用.
主要成果:
- 针对多个数据集的目标检测,在Intersection over Union (IOU) 显著改进:在Fashion-Mnist上为4.83%,在Omniglot上为4.02%,在Cifar-10上为3.89%.
- 在培训后的Mnist数据集上,错误地将"7"类别归类为"1",显著下降了27.32%.
- 证明了基于相关系数的网络的实用性和从积累可靠样本中学习的能力的增强.
结论:
- 拟议的影子节点和基于结构的培训方法增强了基于相关系数的网络,使它们更实用地用于目标检测,特别是在初始数据有限的场景中.
- 这种方法提供了一个非梯度式的参数优化策略,并模仿从少数引用中类似人类的学习,推进一次性学习研究.
相关概念视频
02:07Improving Translational Accuracy
9.2K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.2K
01:10Calibration Curves: Correlation Coefficient
1.6K
In a linear calibration curve, there is a value called the calibration coefficient, denoted by 'r,' which measures the strength and the direction of association between two variables. The correlation coefficient value ranges from −1 to +1. A value of +1 indicates a perfect positive linear correlation, −1 denotes a perfect negative correlation, and 0 implies no correlation between the two variables. A positive correlation value establishes that as one variable increases, the...
1.6K
01:12Types of Errors: Detection and Minimization
1.5K
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
1.5K
00:53Correlation and Regression
1.2K
In statistics, correlation describes the degree of association between two variables. In the subfield of linear regression, correlation is mathematically expressed by the correlation coefficient, which describes the strength and direction of the relationship between two variables. The coefficient is symbolically represented by 'r' and ranges from -1 to +1. A positive value indicates a positive correlation where the two variables move in the same direction. A negative value suggests a...
1.2K
01:20Calibration Curves: Linear Least Squares
1.2K
A calibration curve is a plot of the instrument's response against a series of known concentrations of a substance. This curve is used to set the instrument response levels, using the substance and its concentrations as standards. Alternatively, or additionally, an equation is fitted to the calibration curve plot and subsequently used to calculate the unknown concentrations of other samples reliably.
For data that follow a straight line, the standard method for fitting is the linear...
For data that follow a straight line, the standard method for fitting is the linear...
1.2K
01:00Detection of Gross Error: The Q Test
5.6K
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...
5.6K