Improving the robustness of neural nets in regression tasks is key to their application in multiple domains. Deep learning-based approaches aim to achieve this goal either by improving their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty. We present PIVEN, a deep neural network for producing both a PI and a prediction of specific values. Unlike previous studies, PIVEN makes no assumptions regarding data distribution inside the PI, making its point prediction more effective for various real-world problems. Benchmark experiments show that our approach produces tighter uncertainty bounds than the current state-of-the-art approach for producing PIs, while maintaining comparable performance to the state-of-the-art approach for specific value-prediction. Additional evaluation on large image datasets further support our conclusions.
Eli Simhayev is an M.Sc student in the Department of Software and Information Systems Engineering, at Ben-Gurion University of the Negev (BGU) under the supervision of Dr. Gilad Katz and Prof. Lior Rokach. He holds a B.Sc in Computer Science from Ben-Gurion University. While doing the research and completing the M.Sc degree, he worked a full-time job as an officer in the IDF as a machine learning engineer.