按年被提到
20182023 · 2 次2026
机器学习与深度学习›深度学习理论与泛化·arXiv:1810.05546 · stat.ML

Uncertainty in Neural Networks: Approximately Bayesian Ensembling

Tim Pearce, Felix Leibfried, Alexandra Brintrup, Mohamed Zaki, Andy Neely · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-01-15 · 最近 2023-06-17
2不同的人
2活跃月份
2讨论串
140被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters and data. Ensembling NNs provides an easily implementable, scalable method for uncertainty quantification, however, it has been criticised for not being Bayesian. This work proposes one modification to the usual process that we argue does result in approximate Bayesian inference; regularising parameters about values drawn from a distribution which can be set equal to the prior. A theoretical analysis of the procedure in a simplified setting suggests the recovered posterior is centred correctly but tends to have an underestimated marginal variance, and overestimated correlation. However, two conditions can lead to exact recovery. We argue that these conditions are partially present in NNs. Empirical evaluations demonstrate it has an advantage over standard ensembling, and is competitive with variational methods.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论datastoat · 2023-01

“Indeed, there are Bayesian neural networks and there are non-Bayesian neural networks, and I shouldn't have implied that all neural networks are non-Bayesian. I'm just trying to point out that there is a dichotomy between the Bayesian and the non-Bayesian, and that the standard neural network models are non-Bayesian, and that we need Bayesianism (or some…”

Bayesian statistics and machine learning: How do they differ?原评论 ↗
评论steppi · 2023-06

“I’m not sure if you are aware, but Bayesian neural networks can be actually be well approximated by appropriate ensembles of standard neural networks [0]. The strength of Bayesian nets (including the approximating ensembles) is that they are able to estimate the uncertainty in their own predictions (by generating a probability distribution of possible pre…”

Hello, Perceptron: An introduction to artificial neural networks原评论 ↗