Quantification using Permutation-Invariant Networks based on Histograms

arXiv:2403.15123v1 Announce Type: new
Abstract: Quantification, also known as class prevalence estimation, is the supervised learning task in which a model is trained to predict the prevalence of each class in a given bag of examples. This paper investigates the application of deep neural networks to tasks of quantification in scenarios where it is possible to apply a symmetric supervised approach that eliminates the need for classification as an intermediary step, directly addressing the quantification problem. Additionally, it discusses existing …

abstract application arxiv bag class cs.lg examples histograms networks neural networks paper quantification stat.ml supervised learning tasks type