Uncertainty Quantification in Deep Neural Networks through Statistical Inference on Latent Space
Uncertainty-quantification methods are applied to estimate the confidence of deep-neural-networks classifiers over their predictions. However, most widely used methods are known to be overconfident. We address this problem by developing an algorithm that exploits the latent-space representation of data points fed into the network, to assess the accuracy of their prediction. Using the latent-space representation generated by the fraction of training set that the network classifies correctly, we build a statistical model that is able to capture the likelihood of a given prediction. We show on a synthetic dataset that commonly used methods are mostly overconfident. Overconfidence occurs also for predictions made on data points that are outside the distribution that generated the training data. In contrast, our method can detect such out-of-distribution data points as inaccurately predicted, thus aiding in the automatic detection of outliers.
Code (0)
등록된 구현이 없습니다.
Tasks
Uncertainty QuantificationSimilar Papers 제목 키워드 기반
Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
Stochastic gradient Langevin dynamics combined with Gibbs updates (SGLD--Gibbs) provides a highly scalable approach to approximate Bayesian inference in latent variable models. However, it remains unclear how to tune the…
Bayesian InferenceScalable Bayesian inference for the generalized linear mixed model
The generalized linear mixed model (GLMM) is a popular statistical approach for handling correlated data, and is used extensively in applications areas where big data is common, including biomedical data settings. The fo…
Bayesian InferenceUncertainty QuantificationClassification and Uncertainty Quantification of Corrupted Data using Semi-Supervised Autoencoders
Parametric and non-parametric classifiers often have to deal with real-world data, where corruptions like noise, occlusions, and blur are unavoidable - posing significant challenges. We present a probabilistic approach t…
Uncertainty QuantificationVariational InferenceExchangeable Sequence Models Quantify Uncertainty Over Latent Concepts
Intelligent agents must be able to articulate its own uncertainty. In this work, we show that pre-trained sequence models are naturally capable of probabilistic reasoning over exchangeable data points -- forming informed…
Bayesian InferenceData AugmentationIn-Context LearningTopic Models+2Uncertainty Quantification for Reduced-Order Surrogate Models Applied to Cloud Microphysics
Reduced-order models (ROMs) can efficiently simulate high-dimensional physical systems but lack robust uncertainty quantification methods. Existing approaches are frequently architecture- or training-specific, which limi…