arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.09005cs.LG
收藏

基于核种子网络的可扩展贝叶斯深度学习

Scalable Bayesian Deep Learning with Kernel Seed Networks

The University of Queensland(昆士兰大学)

Sam Maksoud, Kun Zhao, Can Peng, Brian C. Lovell

摘要:

本文讨论了贝叶斯深度神经网络的可扩展性问题。深度神经网络的性能受到了这些算法不确定性校准措施的影响。这限制了它们在计算机辅助诊断和自主车辆导航等高风险领域的应用。贝叶斯深度学习(BDL)为在神经网络中表示不确定性提供了一种很有前途的方法。然而,BDL需要一组单独的参数来存储模型权重的均值和标准差,以学习分布。这导致模型参数的数量增加了2倍。为了解决这个问题,我们提出了一种执行BDL的方法,即内核种子网络(KSN),它不需要增加2倍的参数数量。KSN使用1x1卷积运算来学习参数分布的压缩潜在空间表示。在本文中,我们将展示如何使KSN优于传统的BDL方法,同时减少所需参数的数量高达6.6倍。

英文摘要:

This paper addresses the scalability problem of Bayesian deep neural networks. The performance of deep neural networks is undermined by the fact that these algorithms have poorly calibrated measures of uncertainty. This restricts their application in high risk domains such as computer aided diagnosis and autonomous vehicle navigation. Bayesian Deep Learning (BDL) offers a promising method for representing uncertainty in neural network. However, BDL requires a separate set of parameters to store the mean and standard deviation of model weights to learn a distribution. This results in a prohibitive 2-fold increase in the number of model parameters. To address this problem we present a method for performing BDL, namely Kernel Seed Networks (KSN), which does not require a 2-fold increase in the number of parameters. KSNs use 1x1 Convolution operations to learn a compressed latent space representation of the parameter distribution. In this paper we show how this allows KSNs to outperform conventional BDL methods while reducing the number of required parameters by up to a factor of 6.6.

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。

↑