no code implementations • 12 Jun 2022 • Maryam Hasan, Elke Rundensteiner, Emmanuel Agu
We also study the effect of the size of the fine-tuning dataset on the accuracy of our models.
1 code implementation • NeurIPS 2021 • Walter Gerych, Tom Hartvigsen, Luke Buquicchio, Emmanuel Agu, Elke Rundensteiner
In this work we propose Recurrent Bayesian Classifier Chains (RBCCs), which learn a Bayesian network of class dependencies and leverage this network in order to condition the prediction of child nodes only on their parents.
no code implementations • 1 Jan 2021 • Walter Gerych, Elke Rundensteiner, Emmanuel Agu
OP-DMA succeeds in mapping outliers to low probability regions in the latent space by leveraging a novel Prior-Weighted Loss (PWL) that utilizes the insight that outliers are likely to have a higher reconstruction error than inliers.
no code implementations • 25 Sep 2019 • Walter Gerych, Elke Rundensteiner, Emmanuel Agu
State-of-the-art deep learning methods for outlier detection make the assumption that anomalies will appear far away from inlier data in the latent space produced by distribution mapping deep networks.