论文标题
层析成像自动编码器：无监督的贝叶斯恢复损坏的数据
Tomographic Auto-Encoder: Unsupervised Bayesian Recovery of Corrupted Data
论文作者
论文摘要
我们提出了一种新的概率方法，用于无监督的损坏数据恢复。给定大量退化的样品集合，我们的方法恢复了清洁值的准确后代，从而探索了可能的重建数据的歧管，从而表征了潜在的不确定性。在这种情况下，直接应用经典变异方法通常会导致折叠密度，这些密度无法充分探索解决方案空间。取而代之的是，我们得出了新型的减少熵条件的近似推理方法，从而导致丰倍后期。我们在缺少值和噪声的共同设置下，在数据恢复任务中测试我们的模型，证明了与现有的插补变化方法的卓越性能，并通过不同的实际数据集进行归纳。我们进一步显示了归类后的分类精度，这证明了通过模型传播不确定性的不确定性的优势。
We propose a new probabilistic method for unsupervised recovery of corrupted data. Given a large ensemble of degraded samples, our method recovers accurate posteriors of clean values, allowing the exploration of the manifold of possible reconstructed data and hence characterising the underlying uncertainty. In this setting, direct application of classical variational methods often gives rise to collapsed densities that do not adequately explore the solution space. Instead, we derive our novel reduced entropy condition approximate inference method that results in rich posteriors. We test our model in a data recovery task under the common setting of missing values and noise, demonstrating superior performance to existing variational methods for imputation and de-noising with different real data sets. We further show higher classification accuracy after imputation, proving the advantage of propagating uncertainty to downstream tasks with our model.
