Integrated prediction intervals and specific value predictions for regression problems using neural networks

Eli Simhayev, Gilad Katz, Lior Rokach

Research output: Contribution to journalArticlepeer-review

Abstract

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 IPIV, a deep neural network for producing both a PI and a value prediction. Our loss function expresses the value prediction as a function of the upper and lower bounds, thus ensuring that it falls within the interval without increasing model complexity. Moreover, our approach makes no assumptions regarding data distribution within the PI, making its value prediction more effective for various real-world problems. Experiments and ablation tests on known benchmarks show that our approach produces tighter uncertainty bounds than the current state-of-the-art approaches for producing PIs, while maintaining comparable performance to the state-of-the-art approach for value-prediction. Additionally, we go beyond previous work and include large image datasets in our evaluation, where IPIV is combined with modern neural nets.

Original languageEnglish
Article number108685
JournalKnowledge-Based Systems
Volume247
DOIs
StatePublished - 8 Jul 2022

Keywords

  • Deep learning
  • Prediction intervals
  • Regression

ASJC Scopus subject areas

  • Software
  • Management Information Systems
  • Information Systems and Management
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Integrated prediction intervals and specific value predictions for regression problems using neural networks'. Together they form a unique fingerprint.

Cite this