arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2108.04742cs.LGstat.ML
收藏

属性不确定性的信息:卷积神经网络可以学习输入数据中的错误

The information of attribute uncertainties: what convolutional neural networks can learn about errors in input data

Instituto de Física, Universidade de São Paulo(圣保罗大学物理研究所);Instituto de Matemática e Estatística, Universidade de São Paulo(圣保罗大学数学与统计研究所)

Natália V. N. Rodrigues, L. Raul Abramo, Nina S. Hirata

摘要:

测量误差是衡量数据价值的关键,但在机器学习(ML)中经常被忽视。我们展示了卷积神经网络(CNN)如何能够学习信号和噪声的上下文和模式,从而提高分类方法的性能。我们构建了一个模型,其中两类对象遵循一个基本的高斯分布,其中的功能(输入数据)有不同的,但已知的,噪声水平。该模型模拟了科学数据集的性质,其中噪声是一些随机过程的实现,其基本分布是已知的。然后可以使用标准统计技术(例如,最小二乘最小化或马尔可夫链蒙特卡罗),以及ML技术。这使我们能够利用最大似然方法进行对象分类,并测量ML方法将信息纳入输入数据不确定性的量。我们表明,当每个数据点受到不同程度的噪声(即,具有不同分布函数的噪声),可以通过CNN学习信息,将ML性能提高到至少与最小二乘法相同的水平-有时甚至超过它。此外,我们表明,随着噪声水平的变化,ML分类器的置信度可以作为潜在累积分布函数的代理,但是只有当关于特定输入数据不确定性的信息被提供给CNN时才是如此。

英文摘要:

Errors in measurements are key to weighting the value of data, but are often neglected in Machine Learning (ML). We show how Convolutional Neural Networks (CNNs) are able to learn about the context and patterns of signal and noise, leading to improvements in the performance of classification methods. We construct a model whereby two classes of objects follow an underlying Gaussian distribution, and where the features (the input data) have varying, but known, levels of noise. This model mimics the nature of scientific data sets, where the noises arise as realizations of some random processes whose underlying distributions are known. The classification of these objects can then be performed using standard statistical techniques (e.g., least-squares minimization or Markov-Chain Monte Carlo), as well as ML techniques. This allows us to take advantage of a maximum likelihood approach to object classification, and to measure the amount by which the ML methods are incorporating the information in the input data uncertainties. We show that, when each data point is subject to different levels of noise (i.e., noises with different distribution functions), that information can be learned by the CNNs, raising the ML performance to at least the same level of the least-squares method -- and sometimes even surpassing it. Furthermore, we show that, with varying noise levels, the confidence of the ML classifiers serves as a proxy for the underlying cumulative distribution function, but only if the information about specific input data uncertainties is provided to the CNNs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑