TY - UNPB
T1 - PIVEN
T2 - A Deep Neural Network for Prediction Intervals with Specific Value Prediction.
AU - Simhayev, Eli
AU - Katz, Gilad
AU - Rokach, Lior
N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2020/6/9
Y1 - 2020/6/9
N2 - 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.
AB - 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.
U2 - 10.48550/arXiv.2006.05139
DO - 10.48550/arXiv.2006.05139
M3 - Preprint
BT - PIVEN
ER -