Jeanette Wen Jun Poh

Bayesian Continual Imputation and Prediction For Irregularly Sampled Time Series Data

Learning from irregularly sampled, streaming, multi-variate time-series data with many missing values is a very challenging task. In this paper, we propose a Bayesian Continual Imputation and Prediction for Time-series Data (B-CIPIT), for learning from a sequence of time-series tasks. First, we deve…