An Evidential Neural Network (EN2) is a type of neural network that incorporates elements of evidential reasoning, also known as Dempster-Shafer theory of evidence. The Dempster-Shafer theory is a mathematical framework for reasoning under uncertainty and combining evidence from multiple sources. Evidential neural networks aim to integrate the principles of this theory into the structure and operation of neural networks. Evidential neural networks provide a way to extend traditional neural network models to better handle uncertainty and conflicting evidence, making them suitable for applications where accurate reasoning under uncertainty is crucial.


Multi-Label Temporal Evidential Neural Networks for Early Event Detection

Multi-Label Temporal Evidential Neural Networks for Early Event Detection Early event detection aims to detect events even before the event is complete. However, most of the existing methods focus on an event with a single label but fail to be applied to cases with multiple labels. Another non-negligible issue for early event detection is a prediction with overconfidence due to the high vacuity uncertainty that exists in the early time series. It results in an over-confidence estimation and hence unreliable predictions. To this end, technically, we propose a novel framework, Multi-Label Temporal Evidential Neural Network (MTENN), for multi-label uncertainty estimation in temporal data. MTENN is able to quality predictive uncertainty due to the lack of evidence for multi-label classifications at each time stamp based on belief/evidence theory. In addition, we introduce a novel uncertainty estimation head (weighted binomial comultiplication (WBC)) to quantify the fused uncertainty of a sub-sequence for early event detection. We validate the performance of our approach with state-of-the-art techniques on real-world audio datasets.