Out of Distribution Data Detection Using Dropout Bayesian Neural Networks
André T. Nguyen, Fred Lu, Gary Lopez Munoz, Edward Raff, Charles Nicholas, James Holt
Abstract
We explore the utility of information contained within a dropout based Bayesian neural network (BNN) for the task of detecting out of distribution (OOD) data. We first show how previous attempts to leverage the randomized embeddings induced by the intermediate layers of a dropout BNN can fail due to the distance metric used. We introduce an alternative approach to measuring embedding uncertainty, and demonstrate how incorporating embedding uncertainty improves OOD data identification across three tasks: image classification, language classification, and malware detection.
Topics & Concepts
Dropout (neural networks)Leverage (statistics)Artificial intelligenceComputer scienceEmbeddingBayesian probabilityMalwareArtificial neural networkMachine learningMetric (unit)Pattern recognition (psychology)Data miningBayesian networkEngineeringOperating systemOperations managementAnomaly Detection Techniques and ApplicationsAdversarial Robustness in Machine LearningAdvanced Malware Detection Techniques