arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.04450cs.LGstat.ML
收藏

基于深度Dirichlet混合网络的分类不确定性量化

Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks

University of California, Davis(加州大学戴维斯分校);New York University(纽约大学);University of California, Berkeley(加州大学伯克利分校)

Qingyang Wu, He Li, Lexin Li, Zhou Yu

摘要:

随着深度神经网络在科学和技术领域的广泛成功,量化深度学习产生的预测的不确定性变得越来越重要。在本文中,我们介绍了一种新的方法,该方法使用深度神经网络将显式不确定性声明附加到分类的概率上。准确地说,我们认为分类概率是从一个未知的分布中采样的,我们建议通过狄利克雷混合来学习这个分布,狄利克雷混合足够灵活,可以近似单纯形上的任何连续分布。然后,我们从学习的分布中构造可信区间,以评估分类概率的不确定性。我们的方法易于实现,计算效率高,并且可以与任何深度神经网络架构相结合。我们的方法利用了关键的观察,在许多分类应用程序,如医疗诊断,一个以上的类标签可用于每个观察单位。我们证明了我们的方法的有用性,通过模拟和一个真实的数据例子。

英文摘要:

With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning. In this paper, we introduce a new method that attaches an explicit uncertainty statement to the probabilities of classification using deep neural networks. Precisely, we view that the classification probabilities are sampled from an unknown distribution, and we propose to learn this distribution through the Dirichlet mixture that is flexible enough for approximating any continuous distribution on the simplex. We then construct credible intervals from the learned distribution to assess the uncertainty of the classification probabilities. Our approach is easy to implement, computationally efficient, and can be coupled with any deep neural network architecture. Our method leverages the crucial observation that, in many classification applications such as medical diagnosis, more than one class labels are available for each observational unit. We demonstrate the usefulness of our approach through simulations and a real data example.

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。

↑