arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.02142stat.MLcs.LG
收藏

丢弃作为贝叶斯近似:表示深度学习中的模型不确定性

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

University of Cambridge(剑桥大学)

Yarin Gal, Zoubin Ghahramani

摘要:

深度学习工具在应用机器学习中获得了极大的关注。然而,这种回归和分类工具并不能捕捉模型的不确定性。相比之下,贝叶斯模型提供了一个基于数学的框架来推理模型的不确定性,但通常会带来高昂的计算成本。在本文中,我们开发了一个新的理论框架,将深度神经网络(NN)中的辍学训练作为深度高斯过程中的近似贝叶斯推断。这一理论的直接结果为我们提供了使用dropout NN对不确定性建模的工具-从迄今为止被丢弃的现有模型中提取信息。这缓解了在深度学习中表示不确定性的问题,而不会牺牲计算复杂性或测试准确性。我们进行了广泛的研究辍学的不确定性的性质。以MNIST为例,对回归和分类任务进行了各种网络架构和非线性评估。与现有的最先进的方法相比,我们在预测对数似然和RMSE方面有了相当大的改进,并通过在深度强化学习中使用dropout的不确定性来完成。

英文摘要:

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy. We perform an extensive study of the properties of dropout's uncertainty. Various network architectures and non-linearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods, and finish by using dropout's uncertainty in deep reinforcement learning.

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。

↑