PIVEN: A Deep Neural Network for Prediction Intervals with Specific Value Prediction

Eli Simhayev, Gilad Katz, Lior Rokach. Submitted to NeurIPS 2021 while affiliated with Ben-Gurion University.

Deep learning-based approaches aim to improve the robustness of neural nets in regression by either improving their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty.

This research presents PIVEN, a deep neural network for producing both a PI and a value prediction.