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 2107.07014cs.LGstat.ML
收藏

具有函数概率层的混合贝叶斯神经网络

Hybrid Bayesian Neural Networks with Functional Probabilistic Layers

IBM(国际商业机器公司)

Daniel T. Chang

摘要:

贝叶斯神经网络提供了一种直接和自然的方式来扩展标准深度神经网络,以通过使用概率层来支持概率深度学习,传统上,概率层对权重(和偏差)不确定性进行编码。具体地,混合贝叶斯神经网络利用标准确定性层以及在网络中合理定位的几个概率层来进行不确定性估计。贝叶斯推理的一个主要方面和好处是,先验知识原则上提供了对先验知识进行编码的方法,以用于推理和预测。然而,由于权重没有直观的解释,因此很难指定权重的先验知识。此外,权重的先验与网络计算的函数之间的关系很难表征。相比之下,函数解释起来很直观,并且是直接的,因为它们将输入映射到输出。因此,很自然地指定函数的先验知识来编码先验知识,并将它们用于基于函数的推理和预测。为了支持这一点,我们提出了混合贝叶斯神经网络与功能概率层编码功能(和激活)的不确定性。我们讨论了它们在函数贝叶斯推理、函数变分推理、稀疏高斯过程和稀疏变分高斯过程中的基础。我们进一步使用GPflus进行了一些概念验证实验,GPflus是一个新的库,提供高斯过程层,并支持它们与确定性Keras层一起使用,以形成混合神经网络和高斯过程模型。

英文摘要:

Bayesian neural networks provide a direct and natural way to extend standard deep neural networks to support probabilistic deep learning through the use of probabilistic layers that, traditionally, encode weight (and bias) uncertainty. In particular, hybrid Bayesian neural networks utilize standard deterministic layers together with few probabilistic layers judicially positioned in the networks for uncertainty estimation. A major aspect and benefit of Bayesian inference is that priors, in principle, provide the means to encode prior knowledge for use in inference and prediction. However, it is difficult to specify priors on weights since the weights have no intuitive interpretation. Further, the relationships of priors on weights to the functions computed by networks are difficult to characterize. In contrast, functions are intuitive to interpret and are direct since they map inputs to outputs. Therefore, it is natural to specify priors on functions to encode prior knowledge, and to use them in inference and prediction based on functions. To support this, we propose hybrid Bayesian neural networks with functional probabilistic layers that encode function (and activation) uncertainty. We discuss their foundations in functional Bayesian inference, functional variational inference, sparse Gaussian processes, and sparse variational Gaussian processes. We further perform few proof-of-concept experiments using GPflus, a new library that provides Gaussian process layers and supports their use with deterministic Keras layers to form hybrid neural network and Gaussian process models.

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。

↑