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 1908.07235cs.LGstat.ML
收藏

预测模型不确定性的表示空间密度估计

Density estimation in representation space to predict model uncertainty

Cogent Labs;Apple Inc.(苹果公司)

Tiago Ramalho, Miguel Miranda

摘要:

深度学习模型在使用训练数据集中没有很好表示的测试示例时,经常会做出高置信度的错误预测。我们提出了一种新的和直接的方法来估计预测的不确定性在一个预先训练好的神经网络模型。我们的方法估计的训练数据密度表示空间的一个新的输入。然后,神经网络模型使用这些信息来确定我们是否期望预先训练的模型做出正确的预测。这个不确定性模型是通过预测分布内误差来训练的,但是可以在没有看到任何这样的例子的情况下检测分布外数据。我们测试我们的方法的国家的最先进的图像分类模型中的分布不确定性估计以及分布外检测的设置。

英文摘要:

Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset. We propose a novel and straightforward approach to estimate prediction uncertainty in a pre-trained neural network model. Our method estimates the training data density in representation space for a novel input. A neural network model then uses this information to determine whether we expect the pre-trained model to make a correct prediction. This uncertainty model is trained by predicting in-distribution errors, but can detect out-of-distribution data without having seen any such example. We test our method for a state-of-the art image classification model in the settings of both in-distribution uncertainty estimation as well as out-of-distribution detection.

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。

↑