Generating Survival Interpretable Trajectories and Data

arXiv:2402.12331v1 Announce Type: new
Abstract: A new model for generating survival trajectories and data based on applying an autoencoder of a specific structure is proposed. It solves three tasks. First, it provides predictions in the form of the expected event time and the survival function for a new generated feature vector on the basis of the Beran estimator. Second, the model generates additional data based on a given training set that would supplement the original dataset. Third, the most important, …

abstract arxiv autoencoder cs.ai cs.lg data event feature feature vector form function generated predictions stat.ml survival tasks type vector