Summary of A Comprehensive Survey on Evidential Deep Learning and Its Applications, by Junyu Gao et al.
A Comprehensive Survey on Evidential Deep Learning and Its Applications
by Junyu Gao, Mengyuan Chen, Liangyu Xiang, Changsheng Xu
First submitted to arxiv on: 7 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The novel paradigm of Evidential Deep Learning (EDL) offers reliable uncertainty estimation with minimal additional computation in a single forward pass, crucial for industrial deployment in high-risk applications like autonomous driving and medical diagnosis. EDL’s theoretical foundation lies in subjective logic theory, distinct from other uncertainty estimation frameworks. This survey provides a comprehensive overview of current research on EDL, covering reformulations of evidence collection, improving uncertainty estimation with out-of-distribution samples, various training strategies, and evidential regression networks. Applications across machine learning paradigms and downstream tasks are also explored. The paper concludes with future directions for better performances and broader adoption of EDL. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary EDL is a new way to make deep learning models more reliable by providing uncertainty estimates. This means that the model can tell you how confident it is in its predictions, which is important for applications like self-driving cars or medical diagnosis where mistakes can have serious consequences. The paper explains how EDL works and provides a broad overview of current research in this area. |
Keywords
» Artificial intelligence » Deep learning » Machine learning » Regression
