arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01968cs.LGcs.AIcs.NE
收藏

一种基于丢失规则的贝叶斯神经网络

A Bayesian Neural Network based on Dropout Regulation

Université de Lorraine(洛林大学);CentraleSupélec(巴黎中央理工-高等电力学院);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所)

Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli

摘要:

贝叶斯神经网络(BNN)最近出现在深度学习领域,用于处理分类任务中的不确定性估计,并用于许多应用领域,如天体物理学,自动驾驶等。BNN假设一个先验的神经网络的权重,而不是点估计,使在这种方式的任意和认知的模型预测的不确定性的估计。此外,一个特殊类型的BNN,即MC Dropout,假设一个伯努利分布的权重使用Dropout。有几种尝试来优化辍学率,例如使用变分方法。在本文中,我们提出了一种新的方法,称为“辍学调节”(DR),其包括在训练期间使用如在自动化中使用的控制器来自动调节辍学率。DR允许对不确定性的精确估计,其与最先进的方法相当,同时保持易于实现。

英文摘要:

Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving...BNN assume a prior over the weights of a neural network instead of point estimates, enabling in this way the estimation of both aleatoric and epistemic uncertainty of the model prediction.Moreover, a particular type of BNN, namely MC Dropout, assumes a Bernoulli distribution on the weights by using Dropout.Several attempts to optimize the dropout rate exist, e.g. using a variational approach.In this paper, we present a new method called "Dropout Regulation" (DR), which consists of automatically adjusting the dropout rate during training using a controller as used in automation.DR allows for a precise estimation of the uncertainty which is comparable to the state-of-the-art while remaining simple to implement.

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。

↑