Oates, James T Chapman, DavidPatel, Jay Dhirajlal2023-04-052023-04-052022-01-0112652http://hdl.handle.net/11603/27350In this paper, we present using Cauchy Mixture Model (CMM) as the activation function of deep neural networks for pseudo-labeling in semi-supervised classification. Unlike SoftMax, which is universally used as the final layer activation function, CMM allows the model to identify outliers, i.e., any data that is out of distribution from the observed data. Furthermore, using CMM for pseudo-labeling provides enhanced robustness against confounding bias by preventing the model from yielding high confidence predictions for out-of-distribution data. The proposed method is trained and tested on the CIFAR-10 dataset using only 250, 1000, and 4000 labels. Compared to the baseline of SoftMax-based only supervised and semi-supervised models, the proposed method shows substantial improvements in the same environment setting.application:pdfCauchy Mixture ModelDeep LearningDeep semi-supervisedMachine LearningOutlierSemi supervised LearningText